{"type":"ScholarlyArticle","title":"Complex Query Answering with Neural Link Predictors (Extended Abstract)*","authors":[{"name":"Pasquale Minervini","slug":"pasquale-minervini","given":"Pasquale","family":"Minervini","affiliation":"UCL Centre for Artificial Intelligence , University College London , United Kingdom"},{"name":"Erik Arakelyan","slug":"erik-arakelyan","given":"Erik","family":"Arakelyan","affiliation":"UCL Centre for Artificial Intelligence , University College London , United Kingdom"},{"name":"Daniel Daza","slug":"daniel-daza","given":"Daniel","family":"Daza","affiliation":"Vrije Universiteit Amsterdam , The Netherlands; University of Amsterdam , The Netherlands; Discovery Lab , Elsevier , The Netherlands"},{"name":"Michael Cochez","slug":"michael-cochez","given":"Michael","family":"Cochez","affiliation":"Vrije Universiteit Amsterdam , The Netherlands; Discovery Lab , Elsevier , The Netherlands"}],"abstract":"Neural link predictors are useful for identifying missing edges in large scale Knowledge Graphs. However, it is still not clear how to use these models for answering more complex queries containing logical conjunctions (∧), disjunctions (∨), and existential quantifiers (∃). We propose a framework for efficiently answering complex queries on in- complete Knowledge Graphs. We translate each query into an end-to-end differentiable objective, where the truth value of each atom is computed by a pre-trained neural link predictor. We then analyse two solutions to the optimisation problem, including gradient-based and combinatorial search. In our experiments, the proposed approach produces more accurate results than state-of-the-art methods — black-box models trained on millions of generated queries — without the need for training on a large and diverse set of complex queries. Using orders of magnitude less training data, we obtain relative improvements ranging from 8% up to 40% in Hits@3 across multiple knowledge graphs. We find that it is possible to explain the outcome of our model in terms of the intermediate solutions identified for each of the complex query atoms. All our source code and datasets are available online (https://github.com/uclnlp/cqd).","doi":"10.24963/ijcai.2022/741","url":"https://ijcai.org/proceedings/2022/741","pdf":"https://ijcai.org/proceedings/2022/0741.pdf","markdown":"https://ijcai.org/proceedings/2022/741.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/741","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Sister Conferences Best Papers","track":"Sister Conferences Best Papers","number":741,"pages":{"first":5309,"last":5313},"keywords":["Artificial Intelligence: General"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38987271","length_sec":155,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38985414","length_sec":628,"provider":"slideslive"}],"references":[{"position":1,"raw":"Erik Arakelyan, Daniel Daza, Pasquale Minervini, and Michael Cochez. Complex query answering with neural link predictors. In 9th International Conference on Learn- ing Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net, 2021.","title":"Complex query answering with neural link predictors","authors":"Erik Arakelyan, Daniel Daza, Pasquale Minervini, Michael Cochez","year":"2021","venue":"9th International Conference on Learn-ing Representations, ICLR 2021, Virtual Event","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"Sören Auer, Christian Bizer, Georgi Kobilarov, Jens Lehmann, Richard Cyganiak, and Zachary G. Ives. DB- pedia: A nucleus for a web of open data. In ISWC/ASWC, volume 4825 of Lecture Notes in Computer Science, pages 722-735. Springer, 2007.","title":"DBpedia: A nucleus for a web of open data","authors":"Sören Auer, Christian Bizer, Georgi Kobilarov, Jens Lehmann, Richard Cyganiak, Zachary G Ives","year":"2007","venue":"ISWC/ASWC","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"Antoine Bordes, Nicolas Usunier, Alberto García-Durán, Ja- son Weston, and Oksana Yakhnenko. Translating embed- dings for modeling multi-relational data. In NIPS, pages 2787-2795, 2013.","title":"Translating embeddings for modeling multi-relational data","authors":"Antoine Bordes, Nicolas Usunier, Alberto García-Durán, Jason Weston, Oksana Yakhnenko","year":"2013","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"Nilesh N. Dalvi and Dan Suciu. Efficient query evaluation on probabilistic databases. In VLDB, pages 864-875.","title":"Efficient query evaluation on probabilistic databases","authors":"N Nilesh, Dan Dalvi, Suciu","year":null,"venue":"VLDB","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"Morgan Kaufmann, 2004.","title":null,"authors":"Morgan Kaufmann","year":"2004","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"Brian A. Davey and Hilary A. Priestley. Introduction to Lat- tices and Order, Second Edition. Cambridge University Press, 2002.","title":"Introduction to Lattices and Order, Second Edition","authors":"Brian A Davey, Hilary A Priestley","year":"2002","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"Daniel Daza and Michael Cochez. Message passing query embedding. In ICML Workshop -Graph Representation Learning and Beyond, 2020.","title":"Message passing query embedding","authors":"Daniel Daza, Michael Cochez","year":"2020","venue":"ICML Workshop -Graph Representation Learning and Beyond","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"Michel Dumontier, Alison Callahan, Jose Cruz-Toledo, Pe- ter Ansell, Vincent Emonet, Franc ¸ois Belleau, and Arnaud Droit. Bio2RDF release 3: A larger, more connected network of linked data for the life sciences. In Interna- tional Semantic Web Conference (Posters & Demos), vol- ume 1272 of CEUR Workshop Proceedings, pages 401- 404. CEUR-WS.org, 2014.","title":"Bio2RDF release 3: A larger, more connected network of linked data for the life sciences","authors":"Michel Dumontier, Alison Callahan, Jose Cruz-Toledo, Peter Ansell, Vincent Emonet, Franc ¸ois Belleau, Arnaud Droit","year":"2014","venue":"International Semantic Web Conference (Posters & Demos)","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"William L. Hamilton, Payal Bajaj, Marinka Zitnik, Dan Ju- rafsky, and Jure Leskovec. Embedding logical queries on knowledge graphs. In NeurIPS, pages 2030-2041, 2018.","title":"Embedding logical queries on knowledge graphs","authors":"William L Hamilton, Payal Bajaj, Marinka Zitnik, Dan Jurafsky, Jure Leskovec","year":"2018","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"Daniel S. Himmelstein, Antoine Lizee, Christine Hessler, Leo Brueggeman, Sabrina L. Chen, Dexter Hadley, Ari Green, Pouya Khankhanian, and Sergio E. Baranzini. Systematic integration of biomedical knowledge prioritizes drugs for repurposing. bioRxiv, 2017.","title":"Systematic integration of biomedical knowledge prioritizes drugs for repurposing","authors":"Daniel S Himmelstein, Antoine Lizee, Christine Hessler, Leo Brueggeman, Sabrina L Chen, Dexter Hadley, Ari Green, Pouya Khankhanian, Sergio E Baranzini","year":"2017","venue":"bioRxiv","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"Diederik P. Kingma and Jimmy Ba. Adam: A method for stochastic optimization. In ICLR (Poster), 2015.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":"2015","venue":"ICLR (Poster)","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"Erich-Peter Klement, Radko Mesiar, and Endre Pap. Trian- gular Norms, volume 8 of Trends in Logic. Springer, 2000.","title":"of Trends in Logic","authors":"Erich-Peter Klement, Radko Mesiar, Endre Pap","year":"2000","venue":"Triangular Norms","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"Erich-Peter Klement, Radko Mesiar, and Endre Pap. Triangu- lar norms. position paper I: basic analytical and algebraic properties. Fuzzy Sets Syst., 143(1):5-26, 2004.","title":"Triangular norms. position paper I: basic analytical and algebraic properties","authors":"Erich-Peter Klement, Radko Mesiar, Endre Pap","year":"2004","venue":"Fuzzy Sets Syst","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"Timothée Lacroix, Nicolas Usunier, and Guillaume Obozin- ski. Canonical tensor decomposition for knowledge base completion. In ICML, volume 80 of Proceedings of Ma- chine Learning Research, pages 2869-2878. PMLR, 2018.","title":"Canonical tensor decomposition for knowledge base completion","authors":"Timothée Lacroix, Nicolas Usunier, Guillaume Obozinski","year":"2018","venue":"Proceedings of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"George A. Miller. WORDNET: a lexical database for english. In HLT. Morgan Kaufmann, 1992.","title":"WORDNET: a lexical database for english","authors":"George A Miller","year":"1992","venue":"HLT","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"Tom M. Mitchell, William W. Cohen, Estevam R. Hr- uschka Jr., Partha Pratim Talukdar, Justin Betteridge, An- drew Carlson, Bhavana Dalvi Mishra, Matthew Gardner, Bryan Kisiel, Jayant Krishnamurthy, Ni Lao, Kathryn Mazaitis, Thahir Mohamed, Ndapandula Nakashole, Em- manouil A. Platanios, Alan Ritter, Mehdi Samadi, Burr Settles, Richard C. Wang, Derry Wijaya, Abhinav Gupta, Xinlei Chen, Abulhair Saparov, Malcolm Greaves, and Joel Welling. Never-ending learning. In AAAI, pages 2302- 2310. AAAI Press, 2015.","title":"Never-ending learning","authors":"Tom M Mitchell, William W Cohen, Estevam R Hruschka, Partha Pratim Talukdar, Justin Betteridge, Andrew Carlson, Bhavana Dalvi Mishra, Matthew Gardner, Bryan Kisiel, Jayant Krishnamurthy, Ni Lao, Kathryn Mazaitis, Thahir Mohamed, Ndapandula Nakashole, Emmanouil A Platanios, Alan Ritter, Mehdi Samadi, Burr Settles, Richard C Wang, Derry Wijaya, Abhinav Gupta, Xinlei Chen, Abulhair Saparov, Malcolm Greaves, Joel Welling","year":"2015","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"Maximilian Nickel, Kevin Murphy, Volker Tresp, and Ev- geniy Gabrilovich. A review of relational machine learn- ing for knowledge graphs. Proceedings of the IEEE, 104(1):11-33, 2016.","title":"A review of relational machine learning for knowledge graphs","authors":"Maximilian Nickel, Kevin Murphy, Evgeniy Volker Tresp, Gabrilovich","year":"2016","venue":"Proceedings of the IEEE","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"Natalya Fridman Noy, Yuqing Gao, Anshu Jain, Anant Narayanan, Alan Patterson, and Jamie Taylor. Industry- scale knowledge graphs: lessons and challenges. Commun. ACM, 62(8):36-43, 2019.","title":"Industryscale knowledge graphs: lessons and challenges","authors":"Natalya Fridman Noy, Yuqing Gao, Anshu Jain, Anant Narayanan, Alan Patterson, Jamie Taylor","year":"2019","venue":"Commun. ACM","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"Hongyu Ren and Jure Leskovec. Beta embeddings for multi- hop logical reasoning in knowledge graphs. In Advances in Neural Information Processing Systems 33: Annual Con- ference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, 2020.","title":"Beta embeddings for multihop logical reasoning in knowledge graphs","authors":"Hongyu Ren, Jure Leskovec","year":"2020","venue":"Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"Hongyu Ren, Weihua Hu, and Jure Leskovec. Query2box: Reasoning over knowledge graphs in vector space us- ing box embeddings. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa, Ethiopia, April 26-30, 2020. OpenReview.net, 2020.","title":"Query2box: Reasoning over knowledge graphs in vector space using box embeddings","authors":"Weihua Hongyu Ren, Jure Hu, Leskovec","year":"2020","venue":"8th International Conference on Learning Representations, ICLR 2020","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"Fabian M. Suchanek, Gjergji Kasneci, and Gerhard Weikum. Yago: a core of semantic knowledge. In WWW, pages 697- 706. ACM, 2007.","title":"Yago: a core of semantic knowledge","authors":"Fabian M Suchanek, Gjergji Kasneci, Gerhard Weikum","year":"2007","venue":"WWW","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"Kristina Toutanova and Danqi Chen. Observed versus latent features for knowledge base and text inference. In Pro- ceedings of the 3rd Workshop on Continuous Vector Space Models and their Compositionality, pages 57-66, Beijing, China, July 2015. Association for Computational Linguis- tics.","title":"Observed versus latent features for knowledge base and text inference","authors":"Kristina Toutanova, Danqi Chen","year":"2015","venue":"Proceedings of the 3rd Workshop on Continuous Vector Space Models and their Compositionality","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"Théo Trouillon, Johannes Welbl, Sebastian Riedel, Éric Gaussier, and Guillaume Bouchard. Complex embeddings for simple link prediction. In ICML, volume 48 of JMLR Workshop and Conference Proceedings, pages 2071-2080. JMLR.org, 2016.","title":"Complex embeddings for simple link prediction","authors":"Théo Trouillon, Johannes Welbl, Sebastian Riedel, Éric Gaussier, Guillaume Bouchard","year":"2016","venue":"JMLR Workshop and Conference Proceedings","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"Wenhan Xiong, Thien Hoang, and William Yang Wang. Deeppath: A reinforcement learning method for knowl- edge graph reasoning. In EMNLP, pages 564-573. Asso- ciation for Computational Linguistics, 2017.","title":"Deeppath: A reinforcement learning method for knowledge graph reasoning","authors":"Wenhan Xiong, Thien Hoang, William Yang, Wang","year":"2017","venue":"EMNLP","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}