{"type":"ScholarlyArticle","title":"A Comparative Study of Distributional and Symbolic Paradigms for Relational Learning","authors":[{"name":"Sebastijan Dumancic","slug":"sebastijan-dumancic","given":"Sebastijan","family":"Dumancic","affiliation":"KU Leuven , Belgium"},{"name":"Alberto Garcia-Duran","slug":"alberto-garcia-duran","given":"Alberto","family":"Garcia-Duran","affiliation":"EPFL , Switzerland"},{"name":"Mathias Niepert","slug":"mathias-niepert","given":"Mathias","family":"Niepert","affiliation":"NEC Labs , Germany"}],"abstract":"Many real-world domains can be expressed as graphs and, more generally, as multi-relational knowledge graphs. Though reasoning and learning with knowledge graphs has traditionally been addressed by symbolic approaches such as Statistical relational learning, recent methods in (deep) representation learning have shown promising results for specialised tasks such as knowledge base completion. These approaches, also known as distributional, abandon the traditional symbolic paradigm by replacing symbols with vectors in Euclidean space. With few exceptions, symbolic and distributional approaches are explored in different communities and little is known about their respective strengths and weaknesses. In this work, we compare distributional and symbolic relational learning approaches on various standard relational classification and knowledge base completion tasks. Furthermore, we analyse the properties of the datasets and relate them to the performance of the methods in the comparison. The results reveal possible indicators that could help in choosing one approach over the other for particular knowledge graphs.","doi":"10.24963/ijcai.2019/843","url":"https://ijcai.org/proceedings/2019/843","pdf":"https://ijcai.org/proceedings/2019/0843.pdf","markdown":"https://ijcai.org/proceedings/2019/843.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/843","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Understanding Intelligence and Human-level AI in the New Machine Learning era","track":"Understanding Intelligence and Human-level AI in the New Machine Learning era","number":843,"pages":{"first":6088,"last":6094},"keywords":["Special Track on Understanding Intelligence and Human-level AI in the New Machine Learning era: Neuro Statistical Relational Learning (Special Track on Human AI and Machine Learning)","Special Track on Understanding Intelligence and Human-level AI in the New Machine Learning era: Neural Methods in Inductive Logic Programming (Special Track on Human AI and Machine Learning)","Special Track on Understanding Intelligence and Human-level AI in the New Machine Learning era: Machine Learning and Classical AI (Special Track on Human AI and Machine Learning)"],"videos":[],"references":[{"position":1,"raw":"[Blockeel and De Raedt, 1998] Hendrik Blockeel and Luc De Raedt. Top-down induction of first-order logical de- cision trees. Artificial Intelligence, 101(1-2):285 -297, 1998.","title":"Top-down induction of first-order logical decision trees","authors":"De Blockeel, Hendrik Raedt, Luc Blockeel, Raedt De","year":"1998","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bordes et al., 2013] Antoine Bordes, Nicolas Usunier, Alberto Garcia-Duran, Jason Weston, and Oksana Yakhnenko. Translating embeddings 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 Garcia-Duran, Jason Weston, Oksana Yakhnenko","year":"2013","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[De Raedt et al., 2007] L. De Raedt, A. Kimmig, and H. Toivonen. ProbLog: A probabilistic Prolog and its ap- plication in link discovery. In IJCAI, pages 2462-2467, 2007.","title":"ProbLog: A probabilistic Prolog and its application in link discovery","authors":"L De Raedt, A Kimmig, H Toivonen","year":"2007","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2007/396"},{"position":4,"raw":"[De Raedt et al., 2016] Luc De Raedt, David Poole, Kristian Kersting, and Sriraam Natarajan. Statistical Relational Ar- tificial Intelligence: Logic, Probability, and Computation. Morgan & Claypool Publishers, 2016.","title":"Statistical Relational Artificial Intelligence: Logic, Probability, and Computation","authors":"De Raedt","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Dettmers et al., 2018] Tim Dettmers, Minervini Pasquale, Stenetorp Pontus, and Sebastian Riedel. Convolutional 2d knowledge graph embeddings. In AAAI, February 2018.","title":"Convolutional 2d knowledge graph embeddings","authors":"Tim Dettmers, Minervini Pasquale, Stenetorp Pontus, Sebastian Riedel","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Dumančić and Blockeel, 2017] Sebastijan Dumančić and Hendrik Blockeel. An expressive dissimilarity measure for relational clustering using neighbourhood trees. Machine Learning, 106(9):1523-1545, Oct 2017.","title":"Sebastijan Dumančić and Hendrik Blockeel. An expressive dissimilarity measure for relational clustering using neighbourhood trees","authors":"Blockeel Dumančić","year":"2017","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Dumančić and Blockeel, 2017] Sebastijan Dumančić and Hendrik Blockeel. Clustering-based relational unsuper- vised representation learning with an explicit distributed representation. In IJCAI, pages 1631-1637, 2017.","title":"Sebastijan Dumančić and Hendrik Blockeel. Clustering-based relational unsupervised representation learning with an explicit distributed representation","authors":"Blockeel Dumančić","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Evans and Grefenstette, 2018] Richard Evans and Edward Grefenstette. Learning explanatory rules from noisy data. J. Artif. Intell. Res., 61:1-64, 2018.","title":"Learning explanatory rules from noisy data","authors":"Grefenstette Evans, Richard Evans, Edward Grefenstette","year":"2018","venue":"J. Artif. Intell. Res","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[García-Durán and Niepert, 2018] Alberto García-Durán and Mathias Niepert. Kblrn: End-to-end learning of knowledge base representations with latent, relational, and numerical features. In UAI, pages 372-381, 2018.","title":"Kblrn: End-to-end learning of knowledge base representations with latent, relational, and numerical features","authors":"Alberto García-Durán, Mathias Niepert","year":"2018","venue":"UAI","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Getoor and Taskar, 2007] Lise Getoor and Ben Taskar. In- troduction to Statistical Relational Learning. The MIT Press, 2007.","title":"Introduction to Statistical Relational Learning","authors":"Lise Getoor, Ben Taskar","year":"2007","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Goodfellow et al., 2016] Ian Goodfellow, Yoshua Bengio, and Aaron Courville. Deep Learning. The MIT Press, 2016.","title":"Deep Learning","authors":"Ian Goodfellow, Yoshua Bengio, Aaron Courville","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Grefenstette, 2013] Edward Grefenstette. Towards a formal distributional semantics: Simulating logical calculi with tensors. Proceedings of the Second Joint Conference on Lexical and Computational Semantics, 2013.","title":"Towards a formal distributional semantics: Simulating logical calculi with tensors","authors":"Edward Grefenstette, Grefenstette","year":"2013","venue":"Proceedings of the Second Joint Conference on Lexical and Computational Semantics","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Hamilton et al., 2017] William L. Hamilton, Zhitao Ying, and Jure Leskovec. Representation learning on graphs: Methods and applications. IEEE Data Eng. Bull., 40:52- 74, 2017.","title":"Representation learning on graphs: Methods and applications","authors":"William L Hamilton, Zhitao Ying, Jure Leskovec","year":"2017","venue":"IEEE Data Eng. Bull","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kadlec et al., 2017] Rudolf Kadlec, Ondrej Bajgar, and Jan Kleindienst. Knowledge base completion: Baselines strike back. In Rep4NLP@ACL 2017, pages 69-74, 2017.","title":"Knowledge base completion: Baselines strike back","authors":"Kadlec","year":"2017","venue":"Rep4NLP@ACL 2017","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Landwehr et al., 2006] Niels Landwehr, Andrea Passerini, Luc De Raedt, and Paolo Frasconi. kfoil: Learning simple relational kernels. In AAAI, pages 389-394, 2006.","title":"kfoil: Learning simple relational kernels","authors":"Landwehr","year":"2006","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Manhaeve et al., 2018] Robin Manhaeve, Sebastijan Du- mancic, Angelika Kimmig, Thomas Demeester, and Luc De Raedt. Deepproblog: Neural probabilistic logic pro- gramming. In NeurIPS, pages 3749-3759. 2018.","title":"Robin Manhaeve, Sebastijan Dumancic","authors":"Manhaeve","year":"2018","venue":"Deepproblog: Neural probabilistic logic programming","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Minervini et al., 2017] Pasquale Minervini, Thomas De- meester, Tim Rocktäschel, and Sebastian Riedel. Adver- sarial sets for regularising neural link predictors. In UAI, 2017.","title":"Adversarial sets for regularising neural link predictors","authors":"Pasquale Minervini, Thomas Demeester, Tim Rocktäschel, Sebastian Riedel","year":"2017","venue":"UAI","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Nickel et al., 2014] Maximilian Nickel, Xueyan Jiang, and Volker Tresp. Reducing the rank in relational factorization models by including observable patterns. In NIPS, pages 1179-1187. 2014.","title":"Reducing the rank in relational factorization models by including observable patterns","authors":"Maximilian Nickel, Xueyan Jiang, Volker Tresp","year":"2014","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Nickel et al., 2016] M. Nickel, K. Murphy, V. Tresp, and E. Gabrilovich. A review of relational machine learn- ing for knowledge graphs. Proceedings of the IEEE, 104(1):11-33, Jan 2016.","title":"A review of relational machine learning for knowledge graphs","authors":"M Nickel, K Murphy, V Tresp, E Gabrilovich","year":"2016","venue":"Proceedings of the IEEE","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Pujara et al., 2017] Jay Pujara, Eriq Augustine, and Lise Getoor. Sparsity and noise: Where knowledge graph em- beddings fall short. In EMNLP, 2017.","title":"Sparsity and noise: Where knowledge graph embeddings fall short","authors":"Jay Pujara, Eriq Augustine, Lise Getoor","year":"2017","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Raedt, 2008] Luc De Raedt. Logical and Relational Learn- ing: From ILP to MRDM (Cognitive Technologies). Springer-Verlag, 2008.","title":"Logical and Relational Learning: From ILP to MRDM (Cognitive Technologies)","authors":"Luc Raedt, Raedt De","year":"2008","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Rocktäschel and Riedel, 2017] Tim Rocktäschel and Sebas- tian Riedel. End-to-end differentiable proving. In NIPS, pages 3788-3800. 2017.","title":"Tim Rocktäschel and Sebastian Riedel. End-to-end differentiable proving","authors":"Riedel Rocktäschel","year":"2017","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Schlichtkrull et al., 2018] Michael Sejr Schlichtkrull, Thomas N. Kipf, Peter Bloem, Rianne van den Berg, Ivan Titov, and Max Welling. Modeling relational data with graph convolutional networks. ESWC, 2018.","title":"Modeling relational data with graph convolutional networks","authors":"Sejr Michael, Thomas N Schlichtkrull, Peter Kipf, Rianne Bloem, Van Den, Ivan Berg, Max Titov, Welling","year":"2018","venue":"ESWC","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Schult, 2008] Daniel A. Schult. Exploring network struc- ture, dynamics, and function using networkx. In In Pro- ceedings of the 7th Python in Science Conference (SciPy, pages 11-15, 2008.","title":"Exploring network structure, dynamics, and function using networkx","authors":"A Daniel, Schult","year":"2008","venue":"Proceedings of the 7th Python in Science Conference (SciPy","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Toutanova and Chen, 2015] Kristina Toutanova and Danqi Chen. Observed versus latent features for knowledge base and text inference. In Proceedings of the 3rd Workshop on Continuous Vector Space Models and their Composition- ality, pages 57-66, 2015.","title":"Observed versus latent features for knowledge base and text inference","authors":"Chen ; Toutanova, 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":26,"raw":"[Trouillon et al., 2016] Théo Trouillon, Johannes Welbl, Se- bastian Riedel, Éric Gaussier, and Guillaume Bouchard. Complex embeddings for simple link prediction. In ICML, pages 2071-2080, 2016.","title":"Complex embeddings for simple link prediction","authors":"Théo Trouillon, Johannes Welbl, Sebastian Riedel, Éric Gaussier, Guillaume Bouchard","year":"2016","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Trouillon et al., 2019] Théo Trouillon, Éric Gaussier, Christopher R. Dance, and Guillaume Bouchard. On inductive abilities of latent factor models for relational learning. J. Artif. Intell. Res., 64:21-53, 2019.","title":"On inductive abilities of latent factor models for relational learning","authors":"Éric Théo Trouillon, Christopher R Gaussier, Guillaume Dance, Bouchard","year":"2019","venue":"J. Artif. Intell. Res","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Vig et al., 2018] Lovekesh Vig, Ashwin Srinivasan, Michael Bain, and Ankit Verma. An investigation into the role of domain-knowledge on the use of embeddings. In ILP, pages 169-183. Springer-Verlag, 2018.","title":"An investigation into the role of domain-knowledge on the use of embeddings","authors":"Vig","year":"2018","venue":"ILP","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Wang et al., 2017] Q. Wang, Z. Mao, B. Wang, and L. Guo. Knowledge graph embedding: A survey of approaches and applications. IEEE Transactions on Knowledge and Data Engineering, 29(12):2724-2743, Dec 2017.","title":"Knowledge graph embedding: A survey of approaches and applications","authors":"Q Wang, Z Mao, B Wang, L Guo","year":"2017","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Yang et al., 2015] Bishan Yang, Wen tau Yih, Xiaodong He, Jianfeng Gao, and Li Deng. Embedding entities and rela- tions for learning and inference in knowledge bases. In ICLR, 2015.","title":"Embedding entities and relations for learning and inference in knowledge bases","authors":"Bishan Yang, Wen Tau Yih, Xiaodong He, Jianfeng Gao, Li Deng","year":"2015","venue":"ICLR","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}