{"header":{"numFound":20261,"queryTime":572,"page":1,"pageSize":10},"results":[{"authors":[{"fullName":"Michael Sejr Schlichtkrull","name":null,"surname":null,"rank":1,"pid":{"id":{"scheme":"orcid_pending","value":"0000-0002-8666-0856"},"provenance":null}},{"fullName":"Thomas N. Kipf","name":"Thomas N.","surname":"Kipf","rank":2,"pid":{"id":{"scheme":"orcid","value":"0000-0003-4486-409x"},"provenance":null}},{"fullName":"Peter Bloem","name":null,"surname":null,"rank":3,"pid":{"id":{"scheme":"orcid","value":"0000-0002-0189-5817"},"provenance":null}},{"fullName":"Rianne van den Berg","name":null,"surname":null,"rank":4,"pid":{"id":{"scheme":"orcid_pending","value":"0000-0001-5076-2802"},"provenance":null}},{"fullName":"Ivan Titov 0001","name":null,"surname":null,"rank":5,"pid":null},{"fullName":"Max Welling","name":null,"surname":null,"rank":6,"pid":null}],"openAccessColor":null,"publiclyFunded":false,"type":"publication","language":{"code":"eng","label":"English"},"countries":[{"code":"NL","label":"Netherlands","provenance":null},{"code":"GB","label":"United Kingdom","provenance":null}],"subjects":[{"subject":{"scheme":"keyword","value":"FOS: Computer and information sciences"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computer Science - Machine Learning"},"provenance":null},{"subject":{"scheme":"keyword","value":"Artificial Intelligence (cs.AI)"},"provenance":null},{"subject":{"scheme":"keyword","value":"330"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computer Science - Databases"},"provenance":null},{"subject":{"scheme":"keyword","value":"Statistics - Machine Learning"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computer Science - Artificial Intelligence"},"provenance":null},{"subject":{"scheme":"FOS","value":"0202 electrical engineering, electronic engineering, information engineering"},"provenance":null},{"subject":{"scheme":"keyword","value":"Machine Learning (stat.ML)"},"provenance":null},{"subject":{"scheme":"keyword","value":"Databases (cs.DB)"},"provenance":null},{"subject":{"scheme":"FOS","value":"02 engineering and technology"},"provenance":null},{"subject":{"scheme":"keyword","value":"004"},"provenance":null},{"subject":{"scheme":"keyword","value":"Machine Learning (cs.LG)"},"provenance":null}],"mainTitle":"Modeling Relational Data with Graph Convolutional Networks","subTitle":null,"descriptions":["Knowledge graphs enable a wide variety of applications, including question answering and information retrieval. Despite the great effort invested in their creation and maintenance, even the largest (e.g., Yago, DBPedia or Wikidata) remain incomplete. We introduce Relational Graph Convolutional Networks (R-GCNs) and apply them to two standard knowledge base completion tasks: Link prediction (recovery of missing facts, i.e. subject-predicate-object triples) and entity classification (recovery of missing entity attributes). R-GCNs are related to a recent class of neural networks operating on graphs, and are developed specifically to deal with the highly multi-relational data characteristic of realistic knowledge bases. We demonstrate the effectiveness of R-GCNs as a stand-alone model for entity classification. We further show that factorization models for link prediction such as DistMult can be significantly improved by enriching them with an encoder model to accumulate evidence over multiple inference steps in the relational graph, demonstrating a large improvement of 29.8% on FB15k-237 over a decoder-only baseline."],"publicationDate":"2018-01-01","publisher":"Springer International Publishing","embargoEndDate":"2017-03-01","sources":["Crossref","Lecture Notes in Computer Science ISBN: 9783319934167","Schlichtkrull, M, Kipf, T N, Bloem, P, van den Berg, R, Titov, I & Welling, M 2018, Modeling Relational Data with Graph Convolutional Networks. in A Gangemi, R Navigli, M-E Vidal, P Hitzler, R Troncy, L Hollink, A Tordai & M Alam (eds), The Semantic Web. ESWC 2018.. Lecture Notes in Computer Science (LNCS), vol. 10843, Heraklion, Crete, Greece, pp. 593-607, 15th Extended Semantic Web Conference (ESWC), Heraklion, Greece, 3/06/18. https://doi.org/10.1007/978-3-319-93417-4_38"],"formats":["application/pdf"],"contributors":["Gangemi, Aldo","Navigli, Roberto","Vidal, Maria-Esther","Hitzler, Pascal","Troncy, Raphaël","Hollink, Laura","Tordai, Anna","Alam, Mehwish","Gangemi, A.","Navigli, R.","Vidal, M.-E.","Hitzler, P.","Troncy, R.","Hollink, L.","Tordai, A.","Alam, M."],"coverages":null,"bestAccessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/"},"container":null,"documentationUrls":null,"codeRepositoryUrl":null,"programmingLanguage":null,"contactPeople":null,"contactGroups":null,"tools":null,"size":null,"version":null,"geoLocations":null,"id":"doi_dedup___::79e99f1580af46a0d1924fc20210c00a","originalIds":["10.1007/978-3-319-93417-4_38","50|doiboost____|79e99f1580af46a0d1924fc20210c00a","50|datacite____::cf8fa45abc34600cd5bd08a0f7b11c6b","10.48550/arxiv.1703.06103","oai:arXiv.org:1703.06103","50|od________18::e5bf748a50d752cb79847eade495a34c","50|dblp________::4930dba15c108539cc5975b6388fc653","50|dblp________::a83b90ba2472d3144d7213e21ab20644","50|dris___01178::33af9ede8ea492ded80bc81222d25dd8","oai:dare.uva.nl:openaire_cris_publications/e284086c-e005-4553-8d17-5b72cb273c51","50|dris___01222::3e699932a0f16a8fe2bc6b1e649cd38f","oai:research.vu.nl:openaire_cris_publications/d5f42463-5cc0-477b-ade9-d24490fc3e1c","2604314403","50|od______3094::35184d898441d946707eae4c43dc163e","oai:pure.ed.ac.uk:publications/e5106e47-402e-4728-94b0-b528b1eb0985","ftunivamstpubl:oai:dare.uva.nl:openaire_cris_publications/e284086c-e005-4553-8d17-5b72cb273c51","50|base_oa_____::14e1b64d750b732b690dc5d6b27567bc"],"pids":[{"scheme":"doi","value":"10.1007/978-3-319-93417-4_38"},{"scheme":"doi","value":"10.48550/arxiv.1703.06103"},{"scheme":"arXiv","value":"1703.06103"},{"scheme":"handle","value":"11245.1/e284086c-e005-4553-8d17-5b72cb273c51"},{"scheme":"handle","value":"1871.1/d5f42463-5cc0-477b-ade9-d24490fc3e1c"},{"scheme":"handle","value":"20.500.11820/e5106e47-402e-4728-94b0-b528b1eb0985"}],"dateOfCollection":null,"lastUpdateTimeStamp":null,"indicators":{"citationImpact":{"citationCount":3519.0,"influence":3.1876905E-7,"popularity":2.5645757E-6,"impulse":596.0,"citationClass":"C1","influenceClass":"C1","impulseClass":"C1","popularityClass":"C1"}},"instances":[{"pids":[{"scheme":"doi","value":"10.1007/978-3-319-93417-4_38"}],"license":"Springer Nature TDM","type":"Part of book or chapter of book","urls":["https://doi.org/10.1007/978-3-319-93417-4_38"],"publicationDate":"2018-01-01","refereed":"peerReviewed"},{"pids":[{"scheme":"doi","value":"10.1007/978-3-319-93417-4_38"}],"type":"Part of book or chapter of book","urls":["https://arxiv.org/pdf/1703.06103"],"refereed":"nonPeerReviewed"},{"pids":[{"scheme":"doi","value":"10.48550/arxiv.1703.06103"}],"license":"arXiv Non-Exclusive Distribution","type":"Article","urls":["https://dx.doi.org/10.48550/arxiv.1703.06103"],"publicationDate":"2017-01-01","refereed":"nonPeerReviewed"},{"pids":[{"scheme":"arXiv","value":"1703.06103"}],"type":"Preprint","urls":["http://arxiv.org/abs/1703.06103"],"publicationDate":"2017-03-17","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1007/978-3-319-93417-4_38"}],"type":"Conference object","urls":["https://doi.org/10.1007/978-3-319-93417-4_38","https://dblp.org/rec/conf/esws/SchlichtkrullKB18.html"],"refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"arXiv","value":"1703.06103"}],"type":"Article","urls":["http://arxiv.org/abs/1703.06103","https://dblp.org/rec/journals/corr/SchlichtkrullKB17.html"],"publicationDate":"2017-01-01","refereed":"nonPeerReviewed"},{"pids":[{"scheme":"handle","value":"11245.1/e284086c-e005-4553-8d17-5b72cb273c51"}],"alternateIdentifiers":[{"scheme":"doi","value":"10.1007/978-3-319-93417-4_38"}],"type":"Conference object","urls":["https://hdl.handle.net/11245.1/e284086c-e005-4553-8d17-5b72cb273c51","https://doi.org/10.1007/978-3-319-93417-4_38","https://handle.uba.uva.nl/personal/pure/en/publications/modeling-relational-data-with-graph-convolutional-networks(e284086c-e005-4553-8d17-5b72cb273c51).html"],"publicationDate":"2018-01-01","refereed":"nonPeerReviewed"},{"pids":[{"scheme":"handle","value":"1871.1/d5f42463-5cc0-477b-ade9-d24490fc3e1c"}],"alternateIdentifiers":[{"scheme":"doi","value":"10.1007/978-3-319-93417-4_38"}],"license":"taverne","type":"Conference object","urls":["https://hdl.handle.net/1871.1/d5f42463-5cc0-477b-ade9-d24490fc3e1c","https://doi.org/10.1007/978-3-319-93417-4_38","https://research.vu.nl/en/publications/d5f42463-5cc0-477b-ade9-d24490fc3e1c"],"publicationDate":"2018-01-01","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1007/978-3-319-93417-4_38"},{"scheme":"mag_id","value":"2604314403"}],"type":"Article","urls":["https://dx.doi.org/10.1007/978-3-319-93417-4_38"],"refereed":"nonPeerReviewed"},{"pids":[{"scheme":"handle","value":"20.500.11820/e5106e47-402e-4728-94b0-b528b1eb0985"}],"alternateIdentifiers":[{"scheme":"doi","value":"10.1007/978-3-319-93417-4_38"}],"type":"Conference object","urls":["https://hdl.handle.net/20.500.11820/e5106e47-402e-4728-94b0-b528b1eb0985","https://doi.org/10.1007/978-3-319-93417-4_38","https://www.pure.ed.ac.uk/ws/files/59726746/ESWC2018_paper_4.pdf","https://www.research.ed.ac.uk/en/publications/e5106e47-402e-4728-94b0-b528b1eb0985","https://link.springer.com/chapter/10.1007/978-3-319-93417-4_38"],"publicationDate":"2018-06-03","refereed":"nonPeerReviewed"},{"pids":[{"scheme":"handle","value":"11245.1/e284086c-e005-4553-8d17-5b72cb273c51"}],"alternateIdentifiers":[{"scheme":"doi","value":"10.1007/978-3-319-93417-4_38"}],"type":"Article","urls":["https://doi.org/https://doi.org/10.1007/978-3-319-93417-4_38"],"publicationDate":"2018-01-01","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"mag_id","value":"2604314403"},{"scheme":"doi","value":"10.1007/978-3-319-93417-4_38"}],"type":"Article","urls":["https://dx.doi.org/10.1007/978-3-319-93417-4_38"],"refereed":"nonPeerReviewed"}],"isGreen":true,"isInDiamondJournal":false},{"authors":[{"fullName":"Dettmers, Tim","name":"Tim","surname":"Dettmers","rank":1,"pid":null},{"fullName":"Minervini, Pasquale","name":"Pasquale","surname":"Minervini","rank":2,"pid":{"id":{"scheme":"orcid","value":"0000-0002-8442-602x"},"provenance":null}},{"fullName":"Stenetorp, Pontus","name":"Pontus","surname":"Stenetorp","rank":3,"pid":null},{"fullName":"Riedel, Sebastian","name":"Sebastian","surname":"Riedel","rank":4,"pid":null}],"openAccessColor":null,"publiclyFunded":false,"type":"publication","language":{"code":"und","label":"Undetermined"},"countries":null,"subjects":[{"subject":{"scheme":"keyword","value":"FOS: Computer and information sciences"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computer Science - Machine Learning"},"provenance":null},{"subject":{"scheme":"FOS","value":"0202 electrical engineering, electronic engineering, information engineering"},"provenance":null},{"subject":{"scheme":"FOS","value":"02 engineering and technology"},"provenance":null},{"subject":{"scheme":"keyword","value":"Machine Learning (cs.LG)"},"provenance":null}],"mainTitle":"Convolutional 2D Knowledge Graph Embeddings","subTitle":null,"descriptions":["<jats:p>                Link prediction for knowledge graphs is the task of predicting missing relationships between entities. Previous work on link prediction has focused on shallow, fast models which can scale to large knowledge graphs. However, these models learn less expressive features than deep, multi-layer models — which potentially limits performance. In this work we introduce ConvE, a multi-layer convolutional network model for link prediction, and report state-of-the-art results for several established datasets. We also show that the model is highly parameter efficient, yielding the same performance as DistMult and R-GCN with 8x and 17x fewer parameters. Analysis of our model suggests that it is particularly effective at modelling nodes with high indegree — which are common in highly-connected, complex knowledge graphs such as Freebase and YAGO3. In addition, it has been noted that the WN18 and FB15k datasets suffer from test set leakage, due to inverse relations from the training set being present in the test set — however, the extent of this issue has so far not been quantified. We find this problem to be severe: a simple rule-based model can achieve state-of-the-art results on both WN18 and FB15k. To ensure that models are evaluated on datasets where simply exploiting inverse relations cannot yield competitive results, we investigate and validate several commonly used datasets — deriving robust variants where necessary. We then perform experiments on these robust datasets for our own and several previously proposed models, and find that ConvE achieves state-of-the-art Mean Reciprocal Rank across all datasets.            </jats:p>"],"publicationDate":"2018-04-25","publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","embargoEndDate":"2017-07-01","sources":["Crossref","arXiv:1707.01476"],"formats":null,"contributors":null,"coverages":null,"bestAccessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/"},"container":{"name":"Proceedings of the AAAI Conference on Artificial Intelligence","issnPrinted":"2159-5399","issnOnline":"2374-3468","issnLinking":null,"ep":null,"iss":null,"sp":null,"vol":"32","edition":null,"conferencePlace":null,"conferenceDate":null},"documentationUrls":null,"codeRepositoryUrl":null,"programmingLanguage":null,"contactPeople":null,"contactGroups":null,"tools":null,"size":null,"version":null,"geoLocations":null,"id":"doi_dedup___::52e8fad047b1e6e7bb383bbedc327c5e","originalIds":["10.1609/aaai.v32i1.11573","50|doiboost____|52e8fad047b1e6e7bb383bbedc327c5e","50|datacite____::01216e30e781c471af47575001cffef0","10.5281/zenodo.833287","50|datacite____::3488281d4db877dd1e062faf85152132","10.48550/arxiv.1707.01476","50|datacite____::912ae91cd016e9dd6d5a148c2c3f8c00","10.5281/zenodo.833288","oai:zenodo.org:833288","50|od______2659::912ae91cd016e9dd6d5a148c2c3f8c00","50|od________18::dd7479565e940bfa67c57475e8e31cec","oai:arXiv.org:1707.01476","50|dblp________::03492a7bb1b2b3520093e7036e433bf1","50|dblp________::cb63a80c594a838f0868f2bec85864cc","2964116313","50|r3c4b2081b22::01216e30e781c471af47575001cffef0","50|sygma_______::01216e30e781c471af47575001cffef0"],"pids":[{"scheme":"doi","value":"10.1609/aaai.v32i1.11573"},{"scheme":"doi","value":"10.5281/zenodo.833287"},{"scheme":"doi","value":"10.48550/arxiv.1707.01476"},{"scheme":"doi","value":"10.5281/zenodo.833288"},{"scheme":"arXiv","value":"1707.01476"}],"dateOfCollection":null,"lastUpdateTimeStamp":null,"indicators":{"citationImpact":{"citationCount":1893.0,"influence":1.661786E-7,"popularity":1.3146116E-6,"impulse":292.0,"citationClass":"C1","influenceClass":"C1","impulseClass":"C2","popularityClass":"C1"},"usageCounts":{"downloads":11,"views":11}},"instances":[{"pids":[{"scheme":"doi","value":"10.1609/aaai.v32i1.11573"}],"type":"Article","urls":["https://doi.org/10.1609/aaai.v32i1.11573"],"publicationDate":"2018-04-25","refereed":"peerReviewed"},{"pids":[{"scheme":"doi","value":"10.5281/zenodo.833287"}],"license":"CC BY","type":"Preprint","urls":["https://dx.doi.org/10.5281/zenodo.833287"],"publicationDate":"2017-07-05","refereed":"nonPeerReviewed"},{"pids":[{"scheme":"doi","value":"10.48550/arxiv.1707.01476"}],"license":"arXiv Non-Exclusive Distribution","type":"Article","urls":["https://dx.doi.org/10.48550/arxiv.1707.01476"],"publicationDate":"2017-01-01","refereed":"nonPeerReviewed"},{"pids":[{"scheme":"doi","value":"10.5281/zenodo.833288"}],"license":"CC BY","type":"Preprint","urls":["https://dx.doi.org/10.5281/zenodo.833288"],"publicationDate":"2017-07-05","refereed":"nonPeerReviewed"},{"pids":[{"scheme":"doi","value":"10.5281/zenodo.833288"}],"alternateIdentifiers":[{"scheme":"oai","value":"oai:zenodo.org:833288"}],"license":"CC BY","type":"Preprint","urls":["https://zenodo.org/records/833288","http://dx.doi.org/10.5281/zenodo.833288"],"publicationDate":"2017-07-05","refereed":"nonPeerReviewed"},{"pids":[{"scheme":"arXiv","value":"1707.01476"}],"type":"Preprint","urls":["http://arxiv.org/abs/1707.01476"],"publicationDate":"2017-07-05","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"arXiv","value":"1707.01476"}],"type":"Article","urls":["https://dblp.org/rec/journals/corr/DettmersMSR17.html","http://arxiv.org/abs/1707.01476"],"publicationDate":"2017-01-01","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1609/aaai.v32i1.11573"}],"type":"Conference object","urls":["https://dblp.org/rec/conf/aaai/DettmersMS018.html","https://doi.org/10.1609/aaai.v32i1.11573"],"refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"mag_id","value":"2964116313"},{"scheme":"doi","value":"10.5281/zenodo.833288"}],"type":"Article","urls":["https://dx.doi.org/10.5281/zenodo.833288"],"refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.5281/zenodo.833287"}],"type":"Other literature type","urls":["http://dx.doi.org/10.5281/zenodo.833287"],"publicationDate":"2017-01-01","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.5281/zenodo.833287"}],"license":"CC BY","type":"Article","urls":["https://zenodo.org/record/833288","https://doi.org/10.5281/zenodo.833287"],"publicationDate":"2017-07-05","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"mag_id","value":"2964116313"},{"scheme":"doi","value":"10.5281/zenodo.833288"}],"type":"Article","urls":["https://dx.doi.org/10.5281/zenodo.833288"],"refereed":"nonPeerReviewed"}],"isGreen":true,"isInDiamondJournal":false},{"authors":[{"fullName":"Aidan Hogan","name":null,"surname":null,"rank":1,"pid":{"id":{"scheme":"orcid","value":"0000-0001-9482-1982"},"provenance":null}},{"fullName":"Eva Blomqvist","name":null,"surname":null,"rank":2,"pid":null},{"fullName":"Michael Cochez","name":null,"surname":null,"rank":3,"pid":null},{"fullName":"Claudia d'Amato","name":"Claudia D.","surname":"Amato","rank":4,"pid":null},{"fullName":"Gerard de Melo","name":null,"surname":null,"rank":5,"pid":null},{"fullName":"Claudio Gutierrez 0001","name":null,"surname":null,"rank":6,"pid":{"id":{"scheme":"orcid","value":"0000-0002-4559-6544"},"provenance":null}},{"fullName":"Sabrina Kirrane","name":null,"surname":null,"rank":7,"pid":{"id":{"scheme":"orcid","value":"0000-0002-6955-7718"},"provenance":null}},{"fullName":"José Emilio Labra Gayo","name":null,"surname":null,"rank":8,"pid":{"id":{"scheme":"orcid","value":"0000-0001-8907-5348"},"provenance":null}},{"fullName":"Roberto Navigli","name":null,"surname":null,"rank":9,"pid":{"id":{"scheme":"orcid","value":"0000-0003-3831-9706"},"provenance":null}},{"fullName":"Sebastian Neumaier","name":null,"surname":null,"rank":10,"pid":{"id":{"scheme":"orcid","value":"0000-0002-9804-4882"},"provenance":null}},{"fullName":"Axel-Cyrille Ngonga Ngomo","name":null,"surname":null,"rank":11,"pid":{"id":{"scheme":"orcid","value":"0000-0001-7112-3516"},"provenance":null}},{"fullName":"Axel Polleres","name":null,"surname":null,"rank":12,"pid":null},{"fullName":"Sabbir M. Rashid","name":"Sabbir M.","surname":"Rashid","rank":13,"pid":null},{"fullName":"Anisa Rula","name":null,"surname":null,"rank":14,"pid":{"id":{"scheme":"orcid_pending","value":"0000-0002-8046-7502"},"provenance":null}},{"fullName":"Lukas Schmelzeisen","name":null,"surname":null,"rank":15,"pid":null},{"fullName":"Juan F. Sequeda","name":"Juan F.","surname":"Sequeda","rank":16,"pid":null},{"fullName":"Steffen Staab","name":null,"surname":null,"rank":17,"pid":{"id":{"scheme":"orcid","value":"0000-0002-0780-4154"},"provenance":null}},{"fullName":"Antoine Zimmermann","name":null,"surname":null,"rank":18,"pid":null}],"openAccessColor":"bronze","publiclyFunded":false,"type":"publication","language":{"code":"eng","label":"English"},"countries":[{"code":"FR","label":"France","provenance":null},{"code":"DE","label":"Germany","provenance":null},{"code":"IT","label":"Italy","provenance":null},{"code":"IT","label":"Italy","provenance":null},{"code":"ES","label":"Spain","provenance":null},{"code":"GB","label":"United Kingdom","provenance":null},{"code":"AT","label":"Austria","provenance":null},{"code":"IT","label":"Italy","provenance":null},{"code":"SE","label":"Sweden","provenance":null},{"code":"AT","label":"Austria","provenance":null},{"code":"IT","label":"Italy","provenance":null}],"subjects":[{"subject":{"scheme":"keyword","value":"ddc:004"},"provenance":null},{"subject":{"scheme":"keyword","value":"FOS: Computer and information sciences"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computer Science - Machine Learning"},"provenance":null},{"subject":{"scheme":"keyword","value":"505002 Data protection"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computer Science - Artificial Intelligence"},"provenance":null},{"subject":{"scheme":"keyword","value":"Ontologie"},"provenance":null},{"subject":{"scheme":"keyword","value":"102001 Artificial Intelligence"},"provenance":null},{"subject":{"scheme":"FOS","value":"02 engineering and technology"},"provenance":null},{"subject":{"scheme":"keyword","value":"[INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]"},"provenance":null},{"subject":{"scheme":"keyword","value":"Machine Learning (cs.LG)"},"provenance":null},{"subject":{"scheme":"keyword","value":"502050 Wirtschaftsinformatik"},"provenance":null},{"subject":{"scheme":"keyword","value":"semantic web"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computer Science - Databases"},"provenance":null},{"subject":{"scheme":"keyword","value":"102001 Artificial intelligence"},"provenance":null},{"subject":{"scheme":"FOS","value":"0202 electrical engineering, electronic engineering, information engineering"},"provenance":null},{"subject":{"scheme":"keyword","value":"Knowledge graphs, graph databases, graph query languages, shapes, ontologies, graph algorithms, embeddings, graph neural networks, rule mining"},"provenance":null},{"subject":{"scheme":"keyword","value":"505002 Datenschutz"},"provenance":null},{"subject":{"scheme":"keyword","value":"Graph query language"},"provenance":null},{"subject":{"scheme":"keyword","value":"[INFO]Computer Science [cs]"},"provenance":null},{"subject":{"scheme":"keyword","value":"Knowledge graphs; graph databases; graph query languages; shapes; ontologies; graph algorithms; embeddings; graph neural networks; rule mining"},"provenance":null},{"subject":{"scheme":"keyword","value":"102015 Information systems"},"provenance":null},{"subject":{"scheme":"keyword","value":"102015 Informationssysteme"},"provenance":null},{"subject":{"scheme":"keyword","value":"Knowledge graph"},"provenance":null},{"subject":{"scheme":"keyword","value":"020"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computer Sciences"},"provenance":null},{"subject":{"scheme":"keyword","value":"Institut für Informatik und Computational Science"},"provenance":null},{"subject":{"scheme":"keyword","value":"Graph algorithm"},"provenance":null},{"subject":{"scheme":"keyword","value":"Databases (cs.DB)"},"provenance":null},{"subject":{"scheme":"keyword","value":"Rule mining"},"provenance":null},{"subject":{"scheme":"keyword","value":"artificial intelligence"},"provenance":null},{"subject":{"scheme":"keyword","value":"502050 Business informatics"},"provenance":null},{"subject":{"scheme":"keyword","value":"Graph neural network"},"provenance":null},{"subject":{"scheme":"keyword","value":"[INFO.INFO-MO]Computer Science [cs]/Modeling and Simulation"},"provenance":null},{"subject":{"scheme":"keyword","value":"Graph database"},"provenance":null},{"subject":{"scheme":"keyword","value":"102"},"provenance":null},{"subject":{"scheme":"keyword","value":"004"},"provenance":null},{"subject":{"scheme":"keyword","value":"Embeddings; Graph algorithms; Graph databases; Graph neural networks; Graph query languages; Knowledge graphs; Ontologies; Rule mining; Shapes;"},"provenance":null},{"subject":{"scheme":"keyword","value":"knowledge graphs"},"provenance":null},{"subject":{"scheme":"keyword","value":"machine learning"},"provenance":null},{"subject":{"scheme":"keyword","value":"Datavetenskap (datalogi)"},"provenance":null},{"subject":{"scheme":"keyword","value":"Artificial Intelligence (cs.AI)"},"provenance":null},{"subject":{"scheme":"keyword","value":"Embeddings; Graph algorithms; Graph databases; Graph neural networks; Graph query languages; Knowledge graphs; Ontologies; Rule mining; Shapes"},"provenance":null},{"subject":{"scheme":"keyword","value":"[INFO.INFO-MO] Computer Science [cs]/Modeling and Simulation"},"provenance":null},{"subject":{"scheme":"keyword","value":"Shapes"},"provenance":null},{"subject":{"scheme":"keyword","value":"Embedding"},"provenance":null}],"mainTitle":"Knowledge Graphs","subTitle":null,"descriptions":["<jats:p>In this article, we provide a comprehensive introduction to knowledge graphs, which have recently garnered significant attention from both industry and academia in scenarios that require exploiting diverse, dynamic, large-scale collections of data. After some opening remarks, we motivate and contrast various graph-based data models, as well as languages used to query and validate knowledge graphs. We explain how knowledge can be represented and extracted using a combination of deductive and inductive techniques. We conclude with high-level future research directions for knowledge graphs.</jats:p>"],"publicationDate":"2021-07-02","publisher":"Association for Computing Machinery (ACM)","embargoEndDate":"2020-03-01","sources":["Crossref","Synthesis Lectures on Data, Semantics, and Knowledge ISBN: 9783031007903","Scopus","https://www.scopus.com/inward/record.uri?eid=2-s2.0-85108965182&doi=10.1145%2f3447772&partnerID=40&md5=328ba4bcb19b24906917fdfcf1a06ea9","reponame:RUO. Repositorio Institucional de la Universidad de Oviedo","instname:Universidad de Oviedo (UNIOVI)","ACM Computing Surveys"],"formats":["application/pdf","text"],"contributors":["Breuil, Florent","Hogan, Aidan","Blomqvist, Eva","Cochez, Michael","D'Amato, Claudia","Melo, Gerard de","Gutierrez, Claudio","Kirrane, Sabrina","Gayo, José Emilio Labra","Navigli, Roberto","Neumaier, Sebastian","Ngomo, Axel-Cyrille Ngonga","Polleres, Axel","Rashid, Sabbir M.","Rula, Anisa","Schmelzeisen, Luka","Sequeda, Juan","Staab, Steffen","Zimmermann, Antoine","Millennium Institute for Foundational Research on Data (IMFD)","Pontificia Universidad Católica de Chile (UC)","Department of Computer and Information Science - Linköping University","Linköping University (LIU)","Computer Systems Section - Vrije Universiteit Amsterdam","Vrije Universiteit Amsterdam Amsterdam (VU)","Università degli studi di Bari Aldo Moro = University of Bari Aldo Moro (UNIBA)","Rutgers University System (Rutgers)","Universidad de Oviedo = University of Oviedo","WU Vienna","Department of Informatics and System Sciences (Sapienza University of Rome)","Università degli Studi di Roma \"La Sapienza\" = Sapienza University Rome (UNIROMA)","Universität Paderborn (UPB)","Tetherless World Constellation","Rensselaer Polytechnic Institute (RPI)","Università degli Studi di Milano-Bicocca = University of Milano-Bicocca (UNIMIB)","Universität Bonn = University of Bonn","Universität Koblenz-Landau Koblenz","University of Stuttgart = Universität Stuttgart","University of Southampton","École des Mines de Saint-Étienne (Mines Saint-Étienne MSE)","Institut Mines-Télécom Paris (IMT)","Laboratoire Hubert Curien (LabHC)","Institut d'Optique Graduate School (IOGS)-Université Jean Monnet - Saint-Étienne (UJM)-Centre National de la Recherche Scientifique (CNRS)","Institut Henri Fayol (FAYOL-ENSMSE)","Institut Mines-Télécom Paris (IMT)-Institut Mines-Télécom Paris (IMT)","Département Informatique et systèmes intelligents (FAYOL-ENSMSE)","Ecole Nationale Supérieure des Mines de St Etienne (ENSM ST-ETIENNE)","Mines Saint-Etienne","Hogan, A.","Blomqvist, E.","Cochez, M.","D'Amato, C.","Melo, G. D.","Gutierrez, C.","Kirrane, S.","Gayo, J. E. L.","Navigli, R.","Neumaier, S.","Ngomo, A. -C. N.","Polleres, A.","Rashid, S. M.","Rula, A.","Schmelzeisen, L.","Sequeda, J.","Staab, S.","Zimmermann, A.","Vrije Universiteit Brussel Bruxelles (VUB)","Discovery Lab","Polytechnic University of Bari / Politecnico di Bari","University of Milano","data.world","Laboratoire d'Informatique, de Modélisation et d'Optimisation des Systèmes (LIMOS)","Ecole Nationale Supérieure des Mines de St Etienne (ENSM ST-ETIENNE)-Centre National de la Recherche Scientifique (CNRS)-Université Clermont Auvergne (UCA)-Institut national polytechnique Clermont Auvergne (INP Clermont Auvergne)","Université Clermont Auvergne (UCA)-Université Clermont Auvergne (UCA)"],"coverages":null,"bestAccessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/"},"container":{"name":"ACM Computing Surveys","issnPrinted":"0360-0300","issnOnline":"1557-7341","issnLinking":null,"ep":"37","iss":null,"sp":"1","vol":"54","edition":null,"conferencePlace":null,"conferenceDate":null},"documentationUrls":null,"codeRepositoryUrl":null,"programmingLanguage":null,"contactPeople":null,"contactGroups":null,"tools":null,"size":null,"version":null,"geoLocations":null,"id":"doi_dedup___::2a50b43777588079b733c9d5d2a257c1","originalIds":["10.1145/3447772","50|doiboost____|2a50b43777588079b733c9d5d2a257c1","10.1007/978-3-031-01918-0","50|doiboost____|ebbcf205d723956325c2fe2d085b5800","50|datacite____::d855f6343d27fc621a814cf0967fa09e","10.48550/arxiv.2003.02320","oai:arXiv.org:2003.02320","50|od________18::97335172145f3956ab005806c7cd7d5c","50|RECOLECTA___::9bff5d0436247f6b999f1b64c99ab8c5","oai:digibuo.uniovi.es:10651/61640","50|dblp________::4a1c179bec72fd3249e8de2464a0df8a","50|dblp________::688e7ffb77d3ce2be7be83cd56a0b80e","3010336026","3182825009","oai:research.wu.ac.at:openaire_cris_publications/b7feecc2-3a20-4fdf-ab11-82b6fc6289c1","50|od_____10560::4f599acee0f2796136d447ac7018ec5d","oai:research.wu.ac.at:openaire_cris_publications/853d62c1-f4a0-4208-844a-8a85713a961e","50|od_____10560::b96f26569aca5ddc9527dc6156fe11ea","50|od_____10560::df94948f8fffc44a607524e2f5c18ff6","oai:research.wu.ac.at:openaire_cris_publications/2c39b8a8-b338-4bff-8230-2032021488de","oai:boa.unimib.it:10281/395836","50|od______1299::344e0a1b01644fe4987019f4d9ae04e0","50|od______2439::9bff5d0436247f6b999f1b64c99ab8c5","50|od______2885::867eaea7572240afc5ef7967a0ab57f1","oai:HAL:emse-03440299v1","50|od______2885::bf51cb0178cc488abdc5bb2565fa2f93","oai:HAL:emse-03313702v1","50|od______3662::41baeb2074afc2824dc5e7a030937a44","oai:iris.unibs.it:11379/551223","oai:iris.unibs.it:11379/551221","50|od______3662::d2fed9ef0bcf53d6b2b059e6bfe834f3","oai:iris.uniroma1.it:11573/1589077","50|od______3686::061137f41395247f6f1cd26a6e0b4921","50|od_______261::8cb31c0e9731b0425938376aa4cf0ca0","oai:DiVA.org:liu-179959","oai:kobv.de-opus4-uni-potsdam:68428","50|od_______266::24dc86e85ed67d5fcadd405fd2da604e","50|od_______348::38f79de3d2acb55d8ce2182a1a0b29ae","oai:eprints.soton.ac.uk:446623","50|od_______348::8e8be88c04410e23b7b61b1571207f40","oai:eprints.soton.ac.uk:438786","50|od_______681::8cb31c0e9731b0425938376aa4cf0ca0","50|od_______777::65e723a185fe40e88054c504aea6cb33","oai:epub.wu-wien.ac.at:8214","50|r3c4b2081b22::2a50b43777588079b733c9d5d2a257c1","50|sygma_______::2a50b43777588079b733c9d5d2a257c1","50|base_oa_____::0505ef833189c4e65186f9a254dcc093","ftunivbari:oai:ricerca.uniba.it:11586/378453","ftecoleminesstet:oai:HAL:emse-03109122v1","50|base_oa_____::33570da125273be10137c7d9d0f321f7","ftunivbari:oai:ricerca.uniba.it:11586/378451","50|base_oa_____::44a47f052876f66387b3f298406c4190","ftsouthampton:oai:eprints.soton.ac.uk:446623","50|base_oa_____::4909a994004a92e255c8c9e7e25d7b0e","50|base_oa_____::491dde09e9f76947e52f7284ead75d98","ftunivstetienne:oai:HAL:emse-03109122v1","50|base_oa_____::6d54211245ba5985bccf82294ec72beb","ftecoleminesstet:oai:HAL:emse-03313702v1","ftecoleminesstet:oai:HAL:emse-03440299v1","50|base_oa_____::af9367da0baded0e39449bb35a3939a3","50|base_oa_____::b11c6275503b3b738042dafa8bb226ca","ftsouthampton:oai:eprints.soton.ac.uk:438786"],"pids":[{"scheme":"doi","value":"10.1145/3447772"},{"scheme":"doi","value":"10.1007/978-3-031-01918-0"},{"scheme":"doi","value":"10.48550/arxiv.2003.02320"},{"scheme":"arXiv","value":"2003.02320"},{"scheme":"handle","value":"10651/61640"},{"scheme":"handle","value":"10281/395836"},{"scheme":"handle","value":"11379/551223"},{"scheme":"handle","value":"11379/551221"},{"scheme":"handle","value":"11573/1589077"},{"scheme":"handle","value":"11586/378453"},{"scheme":"handle","value":"11586/378451"}],"dateOfCollection":null,"lastUpdateTimeStamp":null,"indicators":{"citationImpact":{"citationCount":1725.0,"influence":1.334974E-7,"popularity":1.1760344E-6,"impulse":788.0,"citationClass":"C1","influenceClass":"C2","impulseClass":"C1","popularityClass":"C1"}},"instances":[{"pids":[{"scheme":"doi","value":"10.1145/3447772"}],"license":"https://www.acm.org/publications/policies/copyright_policy#Background","type":"Article","urls":["https://doi.org/10.1145/3447772"],"publicationDate":"2021-07-02","refereed":"peerReviewed"},{"pids":[{"scheme":"doi","value":"10.1145/3447772"}],"type":"Article","urls":["https://dl.acm.org/doi/pdf/10.1145/3447772"],"refereed":"nonPeerReviewed"},{"pids":[{"scheme":"doi","value":"10.1007/978-3-031-01918-0"}],"license":"Springer Nature TDM","type":"Book","urls":["https://doi.org/10.1007/978-3-031-01918-0"],"publicationDate":"2022-01-01","refereed":"peerReviewed"},{"pids":[{"scheme":"doi","value":"10.48550/arxiv.2003.02320"}],"license":"arXiv Non-Exclusive Distribution","type":"Article","urls":["https://dx.doi.org/10.48550/arxiv.2003.02320"],"publicationDate":"2020-01-01","refereed":"nonPeerReviewed"},{"pids":[{"scheme":"arXiv","value":"2003.02320"}],"alternateIdentifiers":[{"scheme":"doi","value":"10.1145/3447772"}],"type":"Preprint","urls":["http://arxiv.org/abs/2003.02320"],"publicationDate":"2020-03-04","refereed":"nonPeerReviewed"},{"pids":[{"scheme":"handle","value":"10651/61640"}],"alternateIdentifiers":[{"scheme":"doi","value":"10.1145/3447772"},{"scheme":"doi","value":"10.13039/501100000780horizon2020frameworkprogramme860801"}],"type":"Article","urls":["http://hdl.handle.net/10651/61640","https://dx.doi.org/10.1145/3447772"],"publicationDate":"2021-01-01","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1145/3447772"}],"type":"Article","urls":["https://dblp.org/rec/journals/csur/HoganBCdMGKGNNN21.html","https://doi.org/10.1145/3447772"],"publicationDate":"2022-01-01","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"arXiv","value":"2003.02320"}],"type":"Article","urls":["https://arxiv.org/abs/2003.02320","https://dblp.org/rec/journals/corr/abs-2003-02320.html"],"publicationDate":"2020-01-01","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"mag_id","value":"3010336026"},{"scheme":"doi","value":"10.1145/3447772"}],"type":"Other literature type","urls":["https://dx.doi.org/10.1145/3447772"],"refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1145/3447772"},{"scheme":"mag_id","value":"3182825009"}],"type":"Article","urls":["https://dx.doi.org/10.1145/3447772"],"refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1145/3447772"}],"type":"Article","urls":["https://research.wu.ac.at/de/publications/b7feecc2-3a20-4fdf-ab11-82b6fc6289c1","https://doi.org/10.1145/3447772"],"publicationDate":"2021-01-01","refereed":"nonPeerReviewed"},{"license":"unspecified","type":"Book","urls":["https://research.wu.ac.at/de/publications/853d62c1-f4a0-4208-844a-8a85713a961e"],"publicationDate":"2021-01-01","refereed":"nonPeerReviewed"},{"type":"Research","urls":["https://research.wu.ac.at/de/publications/2c39b8a8-b338-4bff-8230-2032021488de"],"publicationDate":"2020-01-01","refereed":"nonPeerReviewed"},{"pids":[{"scheme":"handle","value":"10281/395836"}],"alternateIdentifiers":[{"scheme":"urn","value":"https://hdl.handle.net/10281/395836"},{"scheme":"doi","value":"10.1145/3447772"},{"scheme":"urn","value":"2-s2.0-85108965182"},{"scheme":"urn","value":"WOS:000670593100011"}],"type":"Article","urls":["https://doi.org/10.1145/3447772","https://hdl.handle.net/10281/395836"],"publicationDate":"2021-01-01","refereed":"nonPeerReviewed"},{"pids":[{"scheme":"handle","value":"10651/61640"}],"alternateIdentifiers":[{"scheme":"doi","value":"10.1145/3447772"}],"type":"Article","urls":["http://hdl.handle.net/10651/61640"],"publicationDate":"2021-01-01","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.2200/s01125ed1v01y202109dsk022"}],"type":"Book","urls":["https://hal-emse.ccsd.cnrs.fr/emse-03440299v1","https://doi.org/10.2200/s01125ed1v01y202109dsk022"],"publicationDate":"2021-01-01","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1145/3447772"},{"scheme":"arXiv","value":"2003.02320"}],"type":"Article","urls":["https://hal-emse.ccsd.cnrs.fr/emse-03313702v1","https://doi.org/10.1145/3447772"],"publicationDate":"2021-01-01","refereed":"nonPeerReviewed"},{"pids":[{"scheme":"handle","value":"11379/551223"}],"alternateIdentifiers":[{"scheme":"doi","value":"10.1145/3447772"},{"scheme":"urn","value":"2-s2.0-85108965182"}],"type":"Article","urls":["https://hdl.handle.net/11379/551223","https://doi.org/10.1145/3447772"],"publicationDate":"2022-01-01","refereed":"nonPeerReviewed"},{"pids":[{"scheme":"handle","value":"11379/551221"}],"alternateIdentifiers":[{"scheme":"doi","value":"10.2200/s01125ed1v01y202109dsk022"}],"type":"Part of book or chapter of book","urls":["https://hdl.handle.net/11379/551221","https://doi.org/10.2200/S01125ED1V01Y202109DSK022"],"publicationDate":"2021-01-01","refereed":"nonPeerReviewed"},{"pids":[{"scheme":"handle","value":"11573/1589077"}],"alternateIdentifiers":[{"scheme":"doi","value":"10.1145/3447772"},{"scheme":"urn","value":"2-s2.0-85108965182"},{"scheme":"urn","value":"WOS:000670593100011"},{"scheme":"urn","value":"http://hdl.handle.net/11573/1589077"}],"license":"CC BY NC ND","type":"Article","urls":["https://doi.org/10.1145/3447772","https://hdl.handle.net/11573/1589077"],"publicationDate":"2021-01-01","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1145/3447772"}],"type":"Article","urls":["http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-179959"],"publicationDate":"2021-01-01","refereed":"peerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1145/3447772"}],"type":"Article","urls":["https://doi.org/10.1145/3447772","https://publishup.uni-potsdam.de/frontdoor/index/index/docId/68428"],"publicationDate":"2021-07-02","refereed":"nonPeerReviewed"},{"type":"Article","urls":["https://eprints.soton.ac.uk/446623/1/ACM_CSUR_crc20210122.pdf"],"publicationDate":"2021-01-20","refereed":"peerReviewed"},{"type":"Book","urls":["https://eprints.soton.ac.uk/438786/1/knowledge_graphs.pdf"],"publicationDate":"2020-03-04","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1145/3447772"}],"type":"Article","urls":["http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-179959"],"publicationDate":"2021-01-01","refereed":"peerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1145/3447772"}],"type":"Article","publicationDate":"2021-01-01","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1145/3447772"}],"type":"Article","urls":["http://dx.doi.org/10.1145/3447772"],"publicationDate":"2021-01-01","refereed":"peerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1145/3447772"}],"type":"Article","urls":["http://dx.doi.org/10.1145/3447772"],"refereed":"nonPeerReviewed"},{"pids":[{"scheme":"handle","value":"11586/378453"}],"alternateIdentifiers":[{"scheme":"doi","value":"10.2200/s01125ed1v01y202109dsk022"}],"type":"Book","urls":["https://doi.org/https://doi.org/10.2200/S01125ED1V01Y202109DSK022"],"publicationDate":"2021-01-01","refereed":"nonPeerReviewed"},{"type":"Report","publicationDate":"2020-01-01","refereed":"nonPeerReviewed"},{"pids":[{"scheme":"handle","value":"11586/378451"}],"alternateIdentifiers":[{"scheme":"doi","value":"10.1145/3447772"}],"type":"Article","urls":["https://doi.org/https://doi.org/10.1145/3447772"],"publicationDate":"2022-01-01","refereed":"nonPeerReviewed"},{"type":"Article","publicationDate":"2021-01-20","refereed":"nonPeerReviewed"},{"type":"Report","publicationDate":"2020-01-01","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1145/3447772"}],"type":"Article","urls":["https://doi.org/https://doi.org/10.1145/3447772"],"publicationDate":"2021-07-01","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.2200/s01125ed1v01y202109dsk022"}],"type":"Book","urls":["https://doi.org/https://doi.org/10.2200/S01125ED1V01Y202109DSK022"],"publicationDate":"2021-11-01","refereed":"nonPeerReviewed"},{"license":"CC BY NC ND","type":"Book","publicationDate":"2020-03-04","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"mag_id","value":"3010336026"},{"scheme":"doi","value":"10.1145/3447772"}],"type":"Other literature type","urls":["https://dx.doi.org/10.1145/3447772"],"refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"mag_id","value":"3182825009"},{"scheme":"doi","value":"10.1145/3447772"}],"type":"Article","urls":["https://dx.doi.org/10.1145/3447772"],"refereed":"nonPeerReviewed"}],"isGreen":true,"isInDiamondJournal":false},{"authors":[{"fullName":"Ji, Shaoxiong","name":"Shaoxiong","surname":"Ji","rank":1,"pid":{"id":{"scheme":"orcid","value":"0000-0003-3281-8002"},"provenance":null}},{"fullName":"Pan, Shirui","name":"Shirui","surname":"Pan","rank":2,"pid":{"id":{"scheme":"orcid","value":"0000-0003-0794-527x"},"provenance":null}},{"fullName":"Cambria, Erik","name":"Erik","surname":"Cambria","rank":3,"pid":{"id":{"scheme":"orcid","value":"0000-0002-3030-1280"},"provenance":null}},{"fullName":"Marttinen, Pekka","name":"Pekka","surname":"Marttinen","rank":4,"pid":{"id":{"scheme":"orcid","value":"0000-0001-7078-7927"},"provenance":null}},{"fullName":"Yu","name":null,"surname":null,"rank":5,"pid":null},{"fullName":"Philip, S.","name":"S.","surname":"Philip","rank":6,"pid":null},{"fullName":"Ji, Shaoxiong","name":"Shaoxiong","surname":"Ji","rank":7,"pid":{"id":{"scheme":"orcid_pending","value":"0000-0003-3281-8002"},"provenance":null}}],"openAccessColor":"bronze","publiclyFunded":false,"type":"publication","language":{"code":"und","label":"Undetermined"},"countries":[{"code":"FI","label":"Finland","provenance":null}],"subjects":[{"subject":{"scheme":"keyword","value":"FOS: Computer and information sciences"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computer Science - Artificial Intelligence"},"provenance":null},{"subject":{"scheme":"keyword","value":"Theory & Methods"},"provenance":null},{"subject":{"scheme":"keyword","value":"relation extraction"},"provenance":null},{"subject":{"scheme":"keyword","value":"representation learning."},"provenance":null},{"subject":{"scheme":"FOS","value":"02 engineering and technology"},"provenance":null},{"subject":{"scheme":"keyword","value":"Hardware & Architecture"},"provenance":null},{"subject":{"scheme":"keyword","value":"Cognition"},"provenance":null},{"subject":{"scheme":"keyword","value":"Artificial Intelligence"},"provenance":null},{"subject":{"scheme":"FOS","value":"0202 electrical engineering, electronic engineering, information engineering"},"provenance":null},{"subject":{"scheme":"keyword","value":"knowledge graph completion (KGC)"},"provenance":null},{"subject":{"scheme":"keyword","value":"Taxonomy"},"provenance":null},{"subject":{"scheme":"keyword","value":"ta113"},"provenance":null},{"subject":{"scheme":"keyword","value":"Science & Technology"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computer Science - Computation and Language"},"provenance":null},{"subject":{"scheme":"keyword","value":"Deep learning"},"provenance":null},{"subject":{"scheme":"keyword","value":"Semantics"},"provenance":null},{"subject":{"scheme":"keyword","value":"Artificial Intelligence (cs.AI)"},"provenance":null},{"subject":{"scheme":"keyword","value":"knowledge graph"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computer Science"},"provenance":null},{"subject":{"scheme":"keyword","value":"Task analysis"},"provenance":null},{"subject":{"scheme":"keyword","value":"Knowledge acquisition"},"provenance":null},{"subject":{"scheme":"keyword","value":"reasoning"},"provenance":null},{"subject":{"scheme":"keyword","value":"Knowledge based systems"},"provenance":null},{"subject":{"scheme":"keyword","value":"Extraterrestrial measurements"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computation and Language (cs.CL)"},"provenance":null},{"subject":{"scheme":"keyword","value":"Neural networks"},"provenance":null}],"mainTitle":"A Survey on Knowledge Graphs: Representation, Acquisition, and Applications","subTitle":null,"descriptions":["Human knowledge provides a formal understanding of the world. Knowledge graphs that represent structural relations between entities have become an increasingly popular research direction towards cognition and human-level intelligence. In this survey, we provide a comprehensive review of knowledge graph covering overall research topics about 1) knowledge graph representation learning, 2) knowledge acquisition and completion, 3) temporal knowledge graph, and 4) knowledge-aware applications, and summarize recent breakthroughs and perspective directions to facilitate future research. We propose a full-view categorization and new taxonomies on these topics. Knowledge graph embedding is organized from four aspects of representation space, scoring function, encoding models, and auxiliary information. For knowledge acquisition, especially knowledge graph completion, embedding methods, path inference, and logical rule reasoning, are reviewed. We further explore several emerging topics, including meta relational learning, commonsense reasoning, and temporal knowledge graphs. To facilitate future research on knowledge graphs, we also provide a curated collection of datasets and open-source libraries on different tasks. In the end, we have a thorough outlook on several promising research directions."],"publicationDate":"2022-02-01","publisher":"Institute of Electrical and Electronics Engineers (IEEE)","embargoEndDate":"2020-02-01","sources":["Crossref"],"formats":["21"],"contributors":["Department of Computer Science","Professorship Marttinen Pekka","Computer Science Professors","Computer Science - Artificial Intelligence and Machine Learning (AIML) - Research area","Monash University Australia","Nanyang Technological University","University of Illinois at Chicago","Aalto-yliopisto","Aalto University"],"coverages":null,"bestAccessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/"},"container":{"name":"IEEE Transactions on Neural Networks and Learning Systems","issnPrinted":"2162-237X","issnOnline":"2162-2388","issnLinking":null,"ep":"514","iss":null,"sp":"494","vol":"33","edition":null,"conferencePlace":null,"conferenceDate":null},"documentationUrls":null,"codeRepositoryUrl":null,"programmingLanguage":null,"contactPeople":null,"contactGroups":null,"tools":null,"size":null,"version":null,"geoLocations":null,"id":"doi_dedup___::2dced7df8233eb141ef4b0c1dca6ac20","originalIds":["10.1109/tnnls.2021.3070843","50|doiboost____|2dced7df8233eb141ef4b0c1dca6ac20","50|datacite____::ff60ff553c33e353ce4f05aae2743407","10.48550/arxiv.2002.00388","33900922","oai:arXiv.org:2002.00388","50|od________18::2ed376362367a5ad226498ec1d482c2f","oai:virta-jtp.csc.fi:Publications/0377906921","50|CSC_________::6e6dc706fefe2fc17e6669c3a525a2fd","50|dblp________::2f0188a0d5663365a3f10dc8103b97fa","50|dblp________::60d56e27d34cea7a5d3f7978c51e9e10","3003265726","oai:aaltodoc.aalto.fi:123456789/107570","50|od_______661::e17d061058f25912aa9a2c1f8c4afa3e","50|researchfi__::9fdf0903c9d2e66a1ac10d47c380947d","50|base_oa_____::7f4522246e8ca9b68d5ddb6fc76c2d92","ftgriffithuniv:oai:research-repository.griffith.edu.au:10072/416709"],"pids":[{"scheme":"doi","value":"10.1109/tnnls.2021.3070843"},{"scheme":"doi","value":"10.48550/arxiv.2002.00388"},{"scheme":"pmid","value":"33900922"},{"scheme":"arXiv","value":"2002.00388"},{"scheme":"handle","value":"10072/416709"}],"dateOfCollection":null,"lastUpdateTimeStamp":null,"indicators":{"citationImpact":{"citationCount":1524.0,"influence":9.871901E-8,"popularity":1.0572385E-6,"impulse":1495.0,"citationClass":"C1","influenceClass":"C2","impulseClass":"C1","popularityClass":"C1"}},"instances":[{"pids":[{"scheme":"doi","value":"10.1109/tnnls.2021.3070843"}],"license":"IEEE Copyright","type":"Article","urls":["https://doi.org/10.1109/tnnls.2021.3070843"],"publicationDate":"2022-02-01","refereed":"peerReviewed"},{"pids":[{"scheme":"doi","value":"10.1109/tnnls.2021.3070843"}],"type":"Article","urls":["http://arxiv.org/pdf/2002.00388"],"refereed":"nonPeerReviewed"},{"pids":[{"scheme":"doi","value":"10.48550/arxiv.2002.00388"}],"license":"arXiv Non-Exclusive Distribution","type":"Article","urls":["https://dx.doi.org/10.48550/arxiv.2002.00388"],"publicationDate":"2020-01-01","refereed":"nonPeerReviewed"},{"pids":[{"scheme":"pmid","value":"33900922"}],"alternateIdentifiers":[{"scheme":"doi","value":"10.1109/tnnls.2021.3070843"}],"type":"Article","urls":["https://pubmed.ncbi.nlm.nih.gov/33900922"],"refereed":"nonPeerReviewed"},{"pids":[{"scheme":"arXiv","value":"2002.00388"}],"alternateIdentifiers":[{"scheme":"doi","value":"10.1109/tnnls.2021.3070843"}],"type":"Preprint","urls":["http://arxiv.org/abs/2002.00388"],"publicationDate":"2020-02-02","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1109/tnnls.2021.3070843"}],"type":"Article","urls":["http://juuli.fi/Record/0377906921","https://doi.org/10.1109/TNNLS.2021.3070843"],"publicationDate":"2021-01-01","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"arXiv","value":"2002.00388"}],"type":"Article","urls":["https://arxiv.org/abs/2002.00388","https://dblp.org/rec/journals/corr/abs-2002-00388.html"],"publicationDate":"2020-01-01","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1109/tnnls.2021.3070843"}],"type":"Article","urls":["https://dblp.org/rec/journals/tnn/JiPCMY22.html","https://doi.org/10.1109/TNNLS.2021.3070843"],"publicationDate":"2022-01-01","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1109/tnnls.2021.3070843"},{"scheme":"mag_id","value":"3003265726"}],"type":"Article","urls":["https://dx.doi.org/10.1109/tnnls.2021.3070843"],"refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1109/tnnls.2021.3070843"}],"type":"Article","urls":["https://aaltodoc.aalto.fi/handle/123456789/107570"],"publicationDate":"2022-02-01","refereed":"peerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1109/tnnls.2021.3070843"}],"type":"Article","urls":["https://doi.org/10.1109/TNNLS.2021.3070843"],"publicationDate":"2021-05-20","refereed":"peerReviewed"},{"pids":[{"scheme":"handle","value":"10072/416709"}],"alternateIdentifiers":[{"scheme":"doi","value":"10.1109/tnnls.2021.3070843"}],"type":"Article","urls":["https://doi.org/https://doi.org/10.1109/TNNLS.2021.3070843"],"publicationDate":"2021-01-01","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"mag_id","value":"3003265726"},{"scheme":"doi","value":"10.1109/tnnls.2021.3070843"}],"type":"Article","urls":["https://dx.doi.org/10.1109/tnnls.2021.3070843"],"refereed":"nonPeerReviewed"}],"isGreen":true,"isInDiamondJournal":false},{"authors":[{"fullName":"Maximilian Nickel","name":null,"surname":null,"rank":1,"pid":{"id":{"scheme":"orcid","value":"0000-0001-5006-0827"},"provenance":null}},{"fullName":"Kevin Murphy 0002","name":null,"surname":null,"rank":2,"pid":null},{"fullName":"Volker Tresp","name":null,"surname":null,"rank":3,"pid":null},{"fullName":"Evgeniy Gabrilovich","name":null,"surname":null,"rank":4,"pid":{"id":{"scheme":"orcid","value":"0000-0001-7933-1926"},"provenance":null}}],"openAccessColor":"bronze","publiclyFunded":false,"type":"publication","language":{"code":"und","label":"Undetermined"},"countries":null,"subjects":[{"subject":{"scheme":"keyword","value":"FOS: Computer and information sciences"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computer Science - Machine Learning"},"provenance":null},{"subject":{"scheme":"keyword","value":"Statistics - Machine Learning"},"provenance":null},{"subject":{"scheme":"FOS","value":"0202 electrical engineering, electronic engineering, information engineering"},"provenance":null},{"subject":{"scheme":"keyword","value":"Machine Learning (stat.ML)"},"provenance":null},{"subject":{"scheme":"FOS","value":"02 engineering and technology"},"provenance":null},{"subject":{"scheme":"keyword","value":"Machine Learning (cs.LG)"},"provenance":null}],"mainTitle":"A Review of Relational Machine Learning for Knowledge Graphs","subTitle":null,"descriptions":["Relational machine learning studies methods for the statistical analysis of relational, or graph-structured, data. In this paper, we provide a review of how such statistical models can be \"trained\" on large knowledge graphs, and then used to predict new facts about the world (which is equivalent to predicting new edges in the graph). In particular, we discuss two fundamentally different kinds of statistical relational models, both of which can scale to massive datasets. The first is based on latent feature models such as tensor factorization and multiway neural networks. The second is based on mining observable patterns in the graph. We also show how to combine these latent and observable models to get improved modeling power at decreased computational cost. Finally, we discuss how such statistical models of graphs can be combined with text-based information extraction methods for automatically constructing knowledge graphs from the Web. To this end, we also discuss Google's Knowledge Vault project as an example of such combination.","To appear in Proceedings of the IEEE"],"publicationDate":"2016-01-01","publisher":"Institute of Electrical and Electronics Engineers (IEEE)","embargoEndDate":"2015-03-01","sources":["Crossref"],"formats":null,"contributors":null,"coverages":null,"bestAccessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/"},"container":{"name":"Proceedings of the IEEE","issnPrinted":"0018-9219","issnOnline":"1558-2256","issnLinking":null,"ep":"33","iss":null,"sp":"11","vol":"104","edition":null,"conferencePlace":null,"conferenceDate":null},"documentationUrls":null,"codeRepositoryUrl":null,"programmingLanguage":null,"contactPeople":null,"contactGroups":null,"tools":null,"size":null,"version":null,"geoLocations":null,"id":"doi_dedup___::d1efb1401e5b403326d7eb18cfb17068","originalIds":["10.1109/jproc.2015.2483592","50|doiboost____|d1efb1401e5b403326d7eb18cfb17068","50|datacite____::637d84b75841206ea5313b491a92965b","10.48550/arxiv.1503.00759","50|od________18::3cb87fc1029e54d8f5dcd5682a2e56cf","oai:arXiv.org:1503.00759","50|dblp________::2ce987d03c6be7c09c930055307afcd7","3100450281","1529533208"],"pids":[{"scheme":"doi","value":"10.1109/jproc.2015.2483592"},{"scheme":"doi","value":"10.48550/arxiv.1503.00759"},{"scheme":"arXiv","value":"1503.00759"}],"dateOfCollection":null,"lastUpdateTimeStamp":null,"indicators":{"citationImpact":{"citationCount":957.0,"influence":9.611482E-8,"popularity":5.243958E-7,"impulse":221.0,"citationClass":"C2","influenceClass":"C2","impulseClass":"C2","popularityClass":"C1"}},"instances":[{"pids":[{"scheme":"doi","value":"10.1109/jproc.2015.2483592"}],"license":"IEEE Copyright","type":"Article","urls":["https://doi.org/10.1109/jproc.2015.2483592"],"publicationDate":"2016-01-01","refereed":"peerReviewed"},{"pids":[{"scheme":"doi","value":"10.1109/jproc.2015.2483592"}],"type":"Article","urls":["http://arxiv.org/pdf/1503.00759"],"refereed":"nonPeerReviewed"},{"pids":[{"scheme":"doi","value":"10.48550/arxiv.1503.00759"}],"license":"arXiv Non-Exclusive Distribution","type":"Article","urls":["https://dx.doi.org/10.48550/arxiv.1503.00759"],"publicationDate":"2015-01-01","refereed":"nonPeerReviewed"},{"pids":[{"scheme":"arXiv","value":"1503.00759"}],"alternateIdentifiers":[{"scheme":"doi","value":"10.1109/jproc.2015.2483592"}],"type":"Preprint","urls":["http://arxiv.org/abs/1503.00759"],"publicationDate":"2015-03-02","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1109/jproc.2015.2483592"}],"type":"Article","urls":["https://dblp.org/rec/journals/pieee/Nickel0TG16.html","https://doi.org/10.1109/JPROC.2015.2483592"],"publicationDate":"2016-01-01","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"mag_id","value":"3100450281"},{"scheme":"mag_id","value":"1529533208"},{"scheme":"doi","value":"10.1109/jproc.2015.2483592"}],"type":"Other literature type","urls":["https://dx.doi.org/10.1109/jproc.2015.2483592"],"refereed":"nonPeerReviewed"}],"isGreen":true,"isInDiamondJournal":false},{"authors":[{"fullName":"Guoliang Ji","name":null,"surname":null,"rank":1,"pid":null},{"fullName":"Shizhu He","name":null,"surname":null,"rank":2,"pid":null},{"fullName":"Liheng Xu","name":null,"surname":null,"rank":3,"pid":null},{"fullName":"Kang Liu 0001","name":null,"surname":null,"rank":4,"pid":null},{"fullName":"Jun Zhao 0001","name":null,"surname":null,"rank":5,"pid":null}],"openAccessColor":null,"publiclyFunded":false,"type":"publication","language":{"code":"und","label":"Undetermined"},"countries":null,"subjects":[{"subject":{"scheme":"FOS","value":"0202 electrical engineering, electronic engineering, information engineering"},"provenance":null},{"subject":{"scheme":"FOS","value":"02 engineering and technology"},"provenance":null},{"subject":{"scheme":"SDG","value":"16. Peace & justice"},"provenance":null}],"mainTitle":"Knowledge Graph Embedding via Dynamic Mapping Matrix","subTitle":null,"descriptions":["Knowledge graphs are useful resources for numerous AI applications, but they are far from completeness. Previous work such as TransE, TransH and TransR/CTransR regard a relation as translation from head entity to tail entity and the CTransR achieves state-of-the-art performance. In this paper, we propose a more fine-grained model named TransD, which is an improvement of TransR/CTransR. In TransD, we use two vectors to represent a named symbol object (entity and relation). The first one represents the meaning of a(n) entity (relation), the other one is used to construct mapping matrix dynamically. Compared with TransR/CTransR, TransD not only considers the diversity of relations, but also entities. TransD has less parameters and has no matrix-vector multiplication operations, which makes it can be applied on large scale graphs. In Experiments, we evaluate our model on two typical tasks including triplets classification and link prediction. Evaluation results show that our approach outperforms state-of-the-art methods."],"publicationDate":"2015-01-01","publisher":"Association for Computational Linguistics (ACL)","embargoEndDate":null,"sources":["Crossref"],"formats":null,"contributors":null,"coverages":null,"bestAccessRight":null,"container":{"name":"Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","issnPrinted":null,"issnOnline":null,"issnLinking":null,"ep":"696","iss":null,"sp":"687","vol":null,"edition":null,"conferencePlace":null,"conferenceDate":null},"documentationUrls":null,"codeRepositoryUrl":null,"programmingLanguage":null,"contactPeople":null,"contactGroups":null,"tools":null,"size":null,"version":null,"geoLocations":null,"id":"doi_dedup___::da1e673544e7e39d4343fe511672583e","originalIds":["10.3115/v1/p15-1067","50|doiboost____|da1e673544e7e39d4343fe511672583e","50|dblp________::46621ebf7d2c2a9febfabc9daace794b","2250342289"],"pids":[{"scheme":"doi","value":"10.3115/v1/p15-1067"}],"dateOfCollection":null,"lastUpdateTimeStamp":null,"indicators":{"citationImpact":{"citationCount":1159.0,"influence":8.626597E-8,"popularity":6.561905E-7,"impulse":65.0,"citationClass":"C2","influenceClass":"C2","impulseClass":"C3","popularityClass":"C1"}},"instances":[{"pids":[{"scheme":"doi","value":"10.3115/v1/p15-1067"}],"type":"Article","urls":["https://doi.org/10.3115/v1/p15-1067"],"publicationDate":"2015-01-01","refereed":"peerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.3115/v1/p15-1067"}],"type":"Conference object","urls":["https://doi.org/10.3115/v1/p15-1067","https://dblp.org/rec/conf/acl/JiHXL015.html"],"refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.3115/v1/p15-1067"},{"scheme":"mag_id","value":"2250342289"}],"type":"Article","urls":["https://dx.doi.org/10.3115/v1/p15-1067"],"refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"mag_id","value":"2250342289"},{"scheme":"doi","value":"10.3115/v1/p15-1067"}],"type":"Article","urls":["https://dx.doi.org/10.3115/v1/p15-1067"],"refereed":"nonPeerReviewed"}],"isGreen":false,"isInDiamondJournal":false},{"authors":[{"fullName":"Paulheim, Heiko","name":"Heiko","surname":"Paulheim","rank":1,"pid":{"id":{"scheme":"orcid","value":"0000-0003-4386-8195"},"provenance":null}}],"openAccessColor":null,"publiclyFunded":false,"type":"publication","language":{"code":"und","label":"Undetermined"},"countries":[{"code":"DE","label":"Germany","provenance":null}],"subjects":[{"subject":{"scheme":"FOS","value":"0202 electrical engineering, electronic engineering, information engineering"},"provenance":null},{"subject":{"scheme":"FOS","value":"02 engineering and technology"},"provenance":null},{"subject":{"scheme":"keyword","value":"004"},"provenance":null}],"mainTitle":"Knowledge graph refinement: A survey of approaches and evaluation methods","subTitle":null,"descriptions":["In the recent years, different Web knowledge graphs, both free and commercial, have been created. While Google coined the term “Knowledge Graph” in 2012, there are also a few openly available knowledge graphs, with DBpedia, YAGO, and Freebase being among the most prominent ones. Those graphs are often constructed from semi-structured knowledge, such as Wikipedia, or harvested from the web with a combination of statistical and linguistic methods. The result are large-scale knowledge graphs that try to make a good trade-off between completeness and correctness. In order to further increase the utility of such knowledge graphs, various refinement methods have been proposed, which try to infer and add missing knowledge to the graph, or identify erroneous pieces of information. In this article, we provide a survey of such knowledge graph refinement approaches, with a dual look at both the methods being proposed as well as the evaluation methodologies used."],"publicationDate":"2016-12-06","publisher":"SAGE Publications","embargoEndDate":null,"sources":["Crossref"],"formats":null,"contributors":["Cimiano, Philipp"],"coverages":null,"bestAccessRight":{"code":"c_14cb","label":"CLOSED","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/"},"container":{"name":"Semantic Web","issnPrinted":"1570-0844","issnOnline":"2210-4968","issnLinking":null,"ep":"508","iss":null,"sp":"489","vol":"8","edition":null,"conferencePlace":null,"conferenceDate":null},"documentationUrls":null,"codeRepositoryUrl":null,"programmingLanguage":null,"contactPeople":null,"contactGroups":null,"tools":null,"size":null,"version":null,"geoLocations":null,"id":"doi_dedup___::2107e4a1710136edf62683a9cc063f0b","originalIds":["10.3233/sw-160218","50|doiboost____|2107e4a1710136edf62683a9cc063f0b","50|medra_______::02a9906f877fb2f6b5ba24e069d435c7","10.3233/SW-160218","50|dblp________::29b89b0b94dcae9d37f67a2a6f368f58","2300469216","oai:ub-madoc.bib.uni-mannheim.de:41515","50|od______2393::e3e567dcb024aec21de772bb2d9cee76"],"pids":[{"scheme":"doi","value":"10.3233/sw-160218"}],"dateOfCollection":null,"lastUpdateTimeStamp":null,"indicators":{"citationImpact":{"citationCount":789.0,"influence":7.1195295E-8,"popularity":4.261075E-7,"impulse":154.0,"citationClass":"C2","influenceClass":"C2","impulseClass":"C2","popularityClass":"C2"}},"instances":[{"pids":[{"scheme":"doi","value":"10.3233/sw-160218"}],"type":"Article","urls":["https://doi.org/10.3233/sw-160218"],"publicationDate":"2016-12-06","refereed":"peerReviewed"},{"pids":[{"scheme":"doi","value":"10.3233/sw-160218"}],"type":"Article","urls":["https://doi.org/10.3233/sw-160218"],"publicationDate":"2016-12-06","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.3233/sw-160218"}],"type":"Article","urls":["https://dblp.org/rec/journals/semweb/Paulheim17.html","https://doi.org/10.3233/SW-160218"],"publicationDate":"2017-01-01","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.3233/sw-160218"},{"scheme":"mag_id","value":"2300469216"}],"type":"Article","urls":["https://dx.doi.org/10.3233/sw-160218"],"refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.3233/sw-160218"}],"type":"Article","urls":["https://madoc.bib.uni-mannheim.de/41515/","https://doi.org/10.3233/sw-160218"],"publicationDate":"2017-01-01","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"mag_id","value":"2300469216"},{"scheme":"doi","value":"10.3233/sw-160218"}],"type":"Article","urls":["https://dx.doi.org/10.3233/sw-160218"],"refereed":"nonPeerReviewed"}],"isGreen":false,"isInDiamondJournal":false},{"authors":[{"fullName":"Xiaojun Chen","name":null,"surname":null,"rank":1,"pid":{"id":{"scheme":"orcid_pending","value":"0000-0003-1091-1361"},"provenance":null}},{"fullName":"Shengbin Jia","name":null,"surname":null,"rank":2,"pid":null},{"fullName":"Yang Xiang","name":null,"surname":null,"rank":3,"pid":null}],"openAccessColor":null,"publiclyFunded":false,"type":"publication","language":{"code":"eng","label":"English"},"countries":null,"subjects":[{"subject":{"scheme":"FOS","value":"0202 electrical engineering, electronic engineering, information engineering"},"provenance":null},{"subject":{"scheme":"FOS","value":"02 engineering and technology"},"provenance":null}],"mainTitle":"A review: Knowledge reasoning over knowledge graph","subTitle":null,"descriptions":["Abstract   Mining valuable hidden knowledge from large-scale data relies on the support of reasoning technology. Knowledge graphs, as a new type of knowledge representation, have gained much attention in natural language processing. Knowledge graphs can effectively organize and represent knowledge so that it can be efficiently utilized in advanced applications. Recently, reasoning over knowledge graphs has become a hot research topic, since it can obtain new knowledge and conclusions from existing data. Herein we review the basic concept and definitions of knowledge reasoning and the methods for reasoning over knowledge graphs. Specifically, we dissect the reasoning methods into three categories: rule-based reasoning, distributed representation-based reasoning and neural network-based reasoning. We also review the related applications of knowledge graph reasoning, such as knowledge graph completion, question answering, and recommender systems. Finally, we discuss the remaining challenges and research opportunities for knowledge graph reasoning."],"publicationDate":"2020-03-01","publisher":"Elsevier BV","embargoEndDate":null,"sources":["Crossref"],"formats":null,"contributors":null,"coverages":null,"bestAccessRight":{"code":"c_14cb","label":"CLOSED","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/"},"container":{"name":"Expert Systems with Applications","issnPrinted":"0957-4174","issnOnline":null,"issnLinking":null,"ep":null,"iss":null,"sp":"112948","vol":"141","edition":null,"conferencePlace":null,"conferenceDate":null},"documentationUrls":null,"codeRepositoryUrl":null,"programmingLanguage":null,"contactPeople":null,"contactGroups":null,"tools":null,"size":null,"version":null,"geoLocations":null,"id":"doi_dedup___::ebeffa1a78d67037ea970cc924991475","originalIds":["S0957417419306669","10.1016/j.eswa.2019.112948","50|doiboost____|ebeffa1a78d67037ea970cc924991475","50|dblp________::a857f03a675051b6956b255278fed356","2972535098"],"pids":[{"scheme":"doi","value":"10.1016/j.eswa.2019.112948"}],"dateOfCollection":null,"lastUpdateTimeStamp":null,"indicators":{"citationImpact":{"citationCount":912.0,"influence":5.558137E-8,"popularity":6.2529523E-7,"impulse":403.0,"citationClass":"C2","influenceClass":"C2","impulseClass":"C1","popularityClass":"C1"}},"instances":[{"pids":[{"scheme":"doi","value":"10.1016/j.eswa.2019.112948"}],"license":"Elsevier TDM","type":"Article","urls":["https://doi.org/10.1016/j.eswa.2019.112948"],"publicationDate":"2020-03-01","refereed":"peerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1016/j.eswa.2019.112948"}],"type":"Article","urls":["https://dblp.org/rec/journals/eswa/ChenJX20.html","https://doi.org/10.1016/j.eswa.2019.112948"],"publicationDate":"2020-01-01","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1016/j.eswa.2019.112948"},{"scheme":"mag_id","value":"2972535098"}],"type":"Article","urls":["https://dx.doi.org/10.1016/j.eswa.2019.112948"],"refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"mag_id","value":"2972535098"},{"scheme":"doi","value":"10.1016/j.eswa.2019.112948"}],"type":"Article","urls":["https://dx.doi.org/10.1016/j.eswa.2019.112948"],"refereed":"nonPeerReviewed"}],"isGreen":false,"isInDiamondJournal":false},{"authors":[{"fullName":"Zhengyan Zhang","name":null,"surname":null,"rank":1,"pid":null},{"fullName":"Xu Han 0007","name":null,"surname":null,"rank":2,"pid":{"id":{"scheme":"orcid","value":"0000-0002-4726-7621"},"provenance":null}},{"fullName":"Zhiyuan Liu 0001","name":null,"surname":null,"rank":3,"pid":null},{"fullName":"Xin Jiang 0002","name":null,"surname":null,"rank":4,"pid":{"id":{"scheme":"orcid","value":"0000-0002-9117-8247"},"provenance":null}},{"fullName":"Maosong Sun 0001","name":null,"surname":null,"rank":5,"pid":null},{"fullName":"Qun Liu 0001","name":null,"surname":null,"rank":6,"pid":null}],"openAccessColor":"hybrid","publiclyFunded":false,"type":"publication","language":{"code":"und","label":"Undetermined"},"countries":null,"subjects":[{"subject":{"scheme":"keyword","value":"FOS: Computer and information sciences"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computer Science - Computation and Language"},"provenance":null},{"subject":{"scheme":"FOS","value":"0202 electrical engineering, electronic engineering, information engineering"},"provenance":null},{"subject":{"scheme":"FOS","value":"02 engineering and technology"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computation and Language (cs.CL)"},"provenance":null}],"mainTitle":"ERNIE: Enhanced Language Representation with Informative Entities","subTitle":null,"descriptions":["Neural language representation models such as BERT pre-trained on large-scale corpora can well capture rich semantic patterns from plain text, and be fine-tuned to consistently improve the performance of various NLP tasks. However, the existing pre-trained language models rarely consider incorporating knowledge graphs (KGs), which can provide rich structured knowledge facts for better language understanding. We argue that informative entities in KGs can enhance language representation with external knowledge. In this paper, we utilize both large-scale textual corpora and KGs to train an enhanced language representation model (ERNIE), which can take full advantage of lexical, syntactic, and knowledge information simultaneously. The experimental results have demonstrated that ERNIE achieves significant improvements on various knowledge-driven tasks, and meanwhile is comparable with the state-of-the-art model BERT on other common NLP tasks. The source code of this paper can be obtained from https://github.com/thunlp/ERNIE.","Accepted by ACL 2019"],"publicationDate":"2019-01-01","publisher":"Association for Computational Linguistics (ACL)","embargoEndDate":"2019-05-01","sources":["Crossref"],"formats":null,"contributors":null,"coverages":null,"bestAccessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/"},"container":{"name":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","issnPrinted":null,"issnOnline":null,"issnLinking":null,"ep":"1451","iss":null,"sp":"1441","vol":null,"edition":null,"conferencePlace":null,"conferenceDate":null},"documentationUrls":null,"codeRepositoryUrl":null,"programmingLanguage":null,"contactPeople":null,"contactGroups":null,"tools":null,"size":null,"version":null,"geoLocations":null,"id":"doi_dedup___::7d1fd7ab16bba20a32ea767d8a2903ca","originalIds":["10.18653/v1/p19-1139","50|doiboost____|7d1fd7ab16bba20a32ea767d8a2903ca","50|datacite____::fff6627973720e1a79b442cb71a5d65c","10.48550/arxiv.1905.07129","50|od________18::521ca07a451b582eb84903dd3215d1c7","oai:arXiv.org:1905.07129","50|dblp________::e9852113b5da0e69350ab70baa77e54c","50|dblp________::ffc10fb4d9a3de0030b2f112d5a54a86","2953356739"],"pids":[{"scheme":"doi","value":"10.18653/v1/p19-1139"},{"scheme":"doi","value":"10.48550/arxiv.1905.07129"},{"scheme":"arXiv","value":"1905.07129"}],"dateOfCollection":null,"lastUpdateTimeStamp":null,"indicators":{"citationImpact":{"citationCount":699.0,"influence":5.1842346E-8,"popularity":4.6815387E-7,"impulse":271.0,"citationClass":"C2","influenceClass":"C2","impulseClass":"C2","popularityClass":"C2"}},"instances":[{"pids":[{"scheme":"doi","value":"10.18653/v1/p19-1139"}],"type":"Article","urls":["https://doi.org/10.18653/v1/p19-1139"],"publicationDate":"2019-01-01","refereed":"peerReviewed"},{"pids":[{"scheme":"doi","value":"10.18653/v1/p19-1139"}],"license":"CC BY","type":"Article","urls":["https://www.aclweb.org/anthology/P19-1139.pdf"],"refereed":"nonPeerReviewed"},{"pids":[{"scheme":"doi","value":"10.48550/arxiv.1905.07129"}],"license":"arXiv Non-Exclusive Distribution","type":"Article","urls":["https://dx.doi.org/10.48550/arxiv.1905.07129"],"publicationDate":"2019-01-01","refereed":"nonPeerReviewed"},{"pids":[{"scheme":"arXiv","value":"1905.07129"}],"type":"Preprint","urls":["http://arxiv.org/abs/1905.07129"],"publicationDate":"2019-05-17","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"arXiv","value":"1905.07129"}],"type":"Article","urls":["http://arxiv.org/abs/1905.07129","https://dblp.org/rec/journals/corr/abs-1905-07129.html"],"publicationDate":"2019-01-01","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.18653/v1/p19-1139"}],"type":"Conference object","urls":["https://dblp.org/rec/conf/acl/ZhangHLJSL19.html","https://doi.org/10.18653/v1/p19-1139"],"refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.18653/v1/p19-1139"},{"scheme":"mag_id","value":"2953356739"}],"type":"Article","urls":["https://dx.doi.org/10.18653/v1/p19-1139"],"refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"mag_id","value":"2953356739"},{"scheme":"doi","value":"10.18653/v1/p19-1139"}],"type":"Article","urls":["https://dx.doi.org/10.18653/v1/p19-1139"],"refereed":"nonPeerReviewed"}],"isGreen":true,"isInDiamondJournal":false},{"authors":[{"fullName":"Maximilian Nickel","name":null,"surname":null,"rank":1,"pid":{"id":{"scheme":"orcid","value":"0000-0001-5006-0827"},"provenance":null}},{"fullName":"Lorenzo Rosasco","name":null,"surname":null,"rank":2,"pid":{"id":{"scheme":"orcid_pending","value":"0000-0003-3098-383x"},"provenance":null}},{"fullName":"Tomaso A. Poggio","name":"Tomaso A.","surname":"Poggio","rank":3,"pid":null}],"openAccessColor":null,"publiclyFunded":false,"type":"publication","language":{"code":"und","label":"Undetermined"},"countries":[{"code":"US","label":"United States","provenance":null},{"code":"IT","label":"Italy","provenance":null}],"subjects":[{"subject":{"scheme":"keyword","value":"Knowledge Graph, Compositional Embeddings, Holographic Embeddings"},"provenance":null},{"subject":{"scheme":"keyword","value":"FOS: Computer and information sciences"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computer Science - Machine Learning"},"provenance":null},{"subject":{"scheme":"keyword","value":"I.2.4"},"provenance":null},{"subject":{"scheme":"keyword","value":"Knowledge Graph"},"provenance":null},{"subject":{"scheme":"keyword","value":"Computer Science - Artificial Intelligence"},"provenance":null},{"subject":{"scheme":"keyword","value":"I.2.6"},"provenance":null},{"subject":{"scheme":"keyword","value":"Machine Learning (stat.ML)"},"provenance":null},{"subject":{"scheme":"FOS","value":"02 engineering and technology"},"provenance":null},{"subject":{"scheme":"keyword","value":"Machine Learning (cs.LG)"},"provenance":null},{"subject":{"scheme":"keyword","value":"Machine Learning"},"provenance":null},{"subject":{"scheme":"keyword","value":"Artificial Intelligence (cs.AI)"},"provenance":null},{"subject":{"scheme":"keyword","value":"Statistics - Machine Learning"},"provenance":null},{"subject":{"scheme":"FOS","value":"0202 electrical engineering, electronic engineering, information engineering"},"provenance":null},{"subject":{"scheme":"keyword","value":"Associative Memory"},"provenance":null},{"subject":{"scheme":"keyword","value":"I.2.6; I.2.4"},"provenance":null}],"mainTitle":"Holographic Embeddings of Knowledge Graphs","subTitle":null,"descriptions":["<jats:p>                Learning embeddings of entities and relations is an efficient and versatile method to perform machine learning on relational data such as knowledge graphs. In this work, we propose holographic embeddings (HolE) to learn compositional  vector space representations of entire knowledge graphs. The proposed method is related to holographic models of associative memory in that it employs circular correlation to create compositional representations. By using correlation as the compositional operator, HolE can capture rich interactions but simultaneously remains efficient to compute, easy to train, and scalable to very large datasets. Experimentally, we show that holographic embeddings are able to outperform state-of-the-art methods for link prediction on knowledge graphs and relational learning benchmark datasets.            </jats:p>"],"publicationDate":"2016-03-02","publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","embargoEndDate":"2015-10-01","sources":["Crossref"],"formats":["application/pdf"],"contributors":["Nickel, Maximilian","Rosasco, Lorenzo","Poggio, Tomaso A","DSpace at My University","McGovern Institute for Brain Research at MIT. Center for Brains, Minds, and Machines","Massachusetts Institute of Technology. Laboratory for Computational and Statistical Learning","McGovern Institute for Brain Research at MIT"],"coverages":null,"bestAccessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/"},"container":{"name":"Proceedings of the AAAI Conference on Artificial Intelligence","issnPrinted":"2159-5399","issnOnline":"2374-3468","issnLinking":null,"ep":null,"iss":null,"sp":null,"vol":"30","edition":null,"conferencePlace":null,"conferenceDate":null},"documentationUrls":null,"codeRepositoryUrl":null,"programmingLanguage":null,"contactPeople":null,"contactGroups":null,"tools":null,"size":null,"version":null,"geoLocations":null,"id":"doi_dedup___::2e2221e1d9f762e8348033a627e59782","originalIds":["10.1609/aaai.v30i1.10314","50|doiboost____|2e2221e1d9f762e8348033a627e59782","50|datacite____::6e89455a822773733b6cea31c43b63fc","10.48550/arxiv.1510.04935","oai:arXiv.org:1510.04935","50|od________18::6692726ba379333e7995daaf73907246","50|dblp________::0eeb8b980e44412761ff8faf7305a62d","50|dblp________::4fb72834634b850a6010e90376a85480","50|od______3710::e4496b33e5e7f7eb2284ba54b0d3fd56","oai:iris.unige.it:11567/888623","oai:dspace.mit.edu:1721.1/112286","50|od________88::061917a9b6680c40ad1da045ed27549c","oai:dspace.mit.edu:1721.1/100203","50|od________88::06ab1224ae68dd6d2fabb3acb339c991","ftmit:oai:dspace.mit.edu:1721.1/100203","50|base_oa_____::47386d915dd6a9a6f35db460cdc54e2e","50|base_oa_____::efd0783b6ff41ef7be4bbbe21866b27b","ftmit:oai:dspace.mit.edu:1721.1/112286"],"pids":[{"scheme":"doi","value":"10.1609/aaai.v30i1.10314"},{"scheme":"doi","value":"10.48550/arxiv.1510.04935"},{"scheme":"arXiv","value":"1510.04935"},{"scheme":"handle","value":"11567/888623"},{"scheme":"handle","value":"1721.1/112286"},{"scheme":"handle","value":"1721.1/100203"}],"dateOfCollection":null,"lastUpdateTimeStamp":null,"indicators":{"citationImpact":{"citationCount":602.0,"influence":5.179029E-8,"popularity":3.7203324E-7,"impulse":83.0,"citationClass":"C2","influenceClass":"C2","impulseClass":"C3","popularityClass":"C2"}},"instances":[{"pids":[{"scheme":"doi","value":"10.1609/aaai.v30i1.10314"}],"type":"Article","urls":["https://doi.org/10.1609/aaai.v30i1.10314"],"publicationDate":"2016-03-02","refereed":"peerReviewed"},{"pids":[{"scheme":"doi","value":"10.48550/arxiv.1510.04935"}],"license":"arXiv Non-Exclusive Distribution","type":"Article","urls":["https://dx.doi.org/10.48550/arxiv.1510.04935"],"publicationDate":"2015-01-01","refereed":"nonPeerReviewed"},{"pids":[{"scheme":"arXiv","value":"1510.04935"}],"type":"Preprint","urls":["http://arxiv.org/abs/1510.04935"],"publicationDate":"2015-10-16","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"arXiv","value":"1510.04935"}],"type":"Article","urls":["https://dblp.org/rec/journals/corr/NickelRP15.html","http://arxiv.org/abs/1510.04935"],"publicationDate":"2015-01-01","refereed":"nonPeerReviewed"},{"alternateIdentifiers":[{"scheme":"doi","value":"10.1609/aaai.v30i1.10314"}],"type":"Conference object","urls":["https://dblp.org/rec/conf/aaai/NickelRP16.html","https://doi.org/10.1609/aaai.v30i1.10314"],"refereed":"nonPeerReviewed"},{"pids":[{"scheme":"handle","value":"11567/888623"}],"alternateIdentifiers":[{"scheme":"urn","value":"2-s2.0-84998671002"},{"scheme":"urn","value":"WOS:000485474201139"},{"scheme":"urn","value":"http://hdl.handle.net/11567/888623"}],"type":"Conference object","urls":["https://hdl.handle.net/11567/888623"],"publicationDate":"2016-01-01","refereed":"nonPeerReviewed"},{"pids":[{"scheme":"handle","value":"1721.1/112286"}],"license":"CC BY NC SA","type":"Article","urls":["https://hdl.handle.net/1721.1/112286"],"publicationDate":"2016-03-01","refereed":"nonPeerReviewed"},{"pids":[{"scheme":"handle","value":"1721.1/100203"}],"license":"CC BY NC","type":"External research report","urls":["https://hdl.handle.net/1721.1/100203"],"publicationDate":"2015-11-16","refereed":"nonPeerReviewed"},{"pids":[{"scheme":"handle","value":"1721.1/100203"}],"license":"CC BY NC","type":"Report","publicationDate":"2015-11-16","refereed":"nonPeerReviewed"},{"pids":[{"scheme":"handle","value":"1721.1/112286"}],"license":"CC BY NC SA","type":"Article","publicationDate":"2017-11-17","refereed":"nonPeerReviewed"}],"isGreen":true,"isInDiamondJournal":false}]}