{"type":"ScholarlyArticle","title":"Deep Learning with Relational Logic Representations","authors":[{"name":"Gustav Sourek","slug":"gustav-sourek","given":"Gustav","family":"Sourek","affiliation":"Czech Technical University in Prague"}],"abstract":"Despite their significant success, all the existing deep neural architectures based on static computational graphs processing fixed tensor representations necessarily face fundamental limitations when presented with dynamically sized and structured data. Examples of these are sparse multi-relational structures present everywhere from biological networks and complex knowledge hyper-graphs to logical theories. Likewise, given the cryptic nature of generalization and representation learning in neural networks, potential integration with the sheer amounts of existing symbolic abstractions present in human knowledge remains highly problematic. Here, we argue that these abilities, naturally present in symbolic approaches based on the expressive power of relational logic, are necessary to be adopted for further progress of neural networks, and present a well founded learning framework for integration of deep and symbolic approaches based on the lifted modelling paradigm.","doi":"10.24963/ijcai.2019/920","url":"https://ijcai.org/proceedings/2019/920","pdf":"https://ijcai.org/proceedings/2019/0920.pdf","markdown":"https://ijcai.org/proceedings/2019/920.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/920","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":"Doctoral Consortium","track":"Doctoral Consortium","number":920,"pages":{"first":6462,"last":6463},"keywords":["Machine Learning: Deep Learning","Machine Learning: Knowledge-based Learning","Machine Learning: Explainable Machine Learning","Machine Learning: Multi-instance;Multi-label;Multi-view learning"],"videos":[],"references":[{"position":1,"raw":"[Garcez et al., 2012] Artur S d'Avila Garcez, Krysia B Broda, and Dov M Gabbay. Neural-symbolic learning sys- tems: foundations and applications. Springer, 2012.","title":"Neural-symbolic learning systems: foundations and applications","authors":"Artur S D'avila, Krysia B Garcez, Dov M Broda, Gabbay","year":"2012","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Niepert et al., 2016] Mathias Niepert, Mohamed Ahmed, and Konstantin Kutzkov. Learning convolutional neural networks for graphs. In Proceedings of ICML, 2016.","title":"Learning convolutional neural networks for graphs","authors":"Mathias Niepert, Mohamed Ahmed, Konstantin Kutzkov","year":"2016","venue":"Proceedings of ICML","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Richardson and Domingos, 2006] Matthew Richardson and Pedro Domingos. Markov logic networks. Machine learn- ing, 2006.","title":"Markov logic networks","authors":"Matthew Richardson, Pedro Domingos","year":"2006","venue":"Machine learning","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Rocktäschel and Riedel, 2017] Tim Rocktäschel and Sebas- tian Riedel. End-to-end differentiable proving. In Ad- vances in Neural Information Processing Systems, 2017.","title":"Tim Rocktäschel and Sebastian Riedel. End-to-end differentiable proving","authors":"Riedel Rocktäschel","year":"2017","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Socher et al., 2011] Richard Socher, Cliff C Lin, Chris Manning, and Andrew Y Ng. Parsing natural scenes and natural language with recursive neural networks. In Pro- ceedings of ICML, 2011.","title":"Parsing natural scenes and natural language with recursive neural networks","authors":"Richard Socher, Cliff C Lin, Chris Manning, Andrew Y Ng","year":"2011","venue":"Proceedings of ICML","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Šourek et al., 2015] Gustav Šourek, Vojtech Aschenbren- ner, Filip Železny, and Ondřej Kuželka. Lifted relational neural networks. In Proceedings of the NIPS CoCo Work- shop: Integrating Neural and Symbolic Approaches, 2015.","title":"Lifted relational neural networks","authors":"Šourek","year":"2015","venue":"Proceedings of the NIPS CoCo Workshop: Integrating Neural and Symbolic Approaches","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Šourek et al., 2016] Gustav Šourek, Suresh Manandhar, Filip Železný, Steven Schockaert, and Ondřej Kuželka. Learning predictive categories using lifted relational neu- ral networks. In Inductive Logic Programming, 2016.","title":"Learning predictive categories using lifted relational neural networks","authors":"Šourek","year":"2016","venue":"Inductive Logic Programming","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Šourek et al., 2017] Gustav Šourek, Martin Svatoš, Filip Železný, Steven Schockaert, and Ondřej Kuželka. Stacked structure learning for lifted relational neural networks. In Inductive Logic Programming, 2017.","title":"Stacked structure learning for lifted relational neural networks","authors":"Šourek","year":"2017","venue":"Inductive Logic Programming","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}