{"type":"ScholarlyArticle","title":"Human-Driven FOL Explanations of Deep Learning","authors":[{"name":"Gabriele Ciravegna","slug":"gabriele-ciravegna","given":"Gabriele","family":"Ciravegna","affiliation":"Department of Information Engineering , University of Florence , Florence , Italy; SAILab , Department of Information Engineering and Mathematics , University of Siena , Siena , Italy"},{"name":"Francesco Giannini","slug":"francesco-giannini","given":"Francesco","family":"Giannini","affiliation":"SAILab , Department of Information Engineering and Mathematics , University of Siena , Siena , Italy"},{"name":"Marco Gori","slug":"marco-gori","given":"Marco","family":"Gori","affiliation":"SAILab , Department of Information Engineering and Mathematics , University of Siena , Siena , Italy; Maasai , Universitè Côte d'Azur , Nice , France"},{"name":"Marco Maggini","slug":"marco-maggini","given":"Marco","family":"Maggini","affiliation":"SAILab , Department of Information Engineering and Mathematics , University of Siena , Siena , Italy"},{"name":"Stefano Melacci","slug":"stefano-melacci","given":"Stefano","family":"Melacci","affiliation":"SAILab , Department of Information Engineering and Mathematics , University of Siena , Siena , Italy"}],"abstract":"Deep neural networks are usually considered black-boxes due to their complex internal architecture, that cannot straightforwardly provide human-understandable explanations on how they behave. Indeed, Deep Learning is still viewed with skepticism in those real-world domains in which incorrect predictions may produce critical effects. This is one of the reasons why in the last few years Explainable Artificial Intelligence (XAI) techniques have gained a lot of attention in the scientific community. In this paper, we focus on the case of multi-label classification, proposing a neural network that learns the relationships among the predictors associated to each class, yielding First-Order Logic (FOL)-based descriptions. Both the explanation-related network and the classification-related network are jointly learned, thus implicitly introducing a latent dependency between the development of the explanation mechanism and the development of the classifiers. Our model can integrate human-driven preferences that guide the learning-to-explain process, and it is presented in a unified framework. Different typologies of explanations are evaluated in distinct experiments, showing that the proposed approach discovers new knowledge and can improve the classifier performance.","doi":"10.24963/ijcai.2020/309","url":"https://ijcai.org/proceedings/2020/309","pdf":"https://ijcai.org/proceedings/2020/0309.pdf","markdown":"https://ijcai.org/proceedings/2020/309.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/309","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Machine Learning","track":"Main track","number":309,"pages":{"first":2234,"last":2240},"keywords":["Machine Learning: Neuro-Symbolic Methods","Machine Learning: Interpretability","Machine Learning: Explainable Machine Learning"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/25236/file_25236.m3u8","length_sec":272,"provider":"hls"}],"references":[{"position":1,"raw":"[Betti et al., 2019] Alessandro Betti, Marco Gori, and Ste- fano Melacci. Cognitive action laws: The case of visual features. IEEE transactions on neural networks and learn- ing systems, 2019.","title":"Cognitive action laws: The case of visual features","authors":"Alessandro Betti, Marco Gori, Stefano Melacci","year":"2019","venue":"IEEE transactions on neural networks and learning systems","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bibal and Frénay, 2016] Adrien Bibal and Benoît Frénay. Interpretability of machine learning models and represen- tations: an introduction. In ESANN, 2016.","title":"Adrien Bibal and Benoît Frénay. Interpretability of machine learning models and representations: an introduction","authors":"Frénay Bibal","year":"2016","venue":"ESANN","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Carvalho et al., 2019] Diogo V Carvalho, Eduardo M Pereira, and Jaime S Cardoso. Machine learning inter- pretability: A survey on methods and metrics. Electronics, 8(8):832, 2019.","title":"Machine learning interpretability: A survey on methods and metrics","authors":"Eduardo M Diogo V Carvalho, Jaime S Pereira, Cardoso","year":"2019","venue":"Electronics","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Donadello et al., 2017] Ivan Donadello, Luciano Serafini, and Artur d'Avila Garcez. Logic tensor networks for semantic image interpretation. arXiv preprint arXiv:1705.08968, 2017.","title":"Logic tensor networks for semantic image interpretation","authors":"Ivan Donadello, Luciano Serafini, Artur D'avila Garcez","year":"2017","venue":null,"doi":null,"url":null,"internal_url":"/proceedings/2017/221"},{"position":5,"raw":"[Doshi-Velez and Kim, 2017] Finale Doshi-Velez and Been Kim. Towards a rigorous science of interpretable machine learning. arXiv preprint arXiv:1702.08608, 2017.","title":"Finale Doshi-Velez and Been Kim. Towards a rigorous science of interpretable machine learning","authors":"Kim Doshi-Velez","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Došilović et al., 2018] Filip Karlo Došilović, Mario Brčić, and Nikica Hlupić. Explainable artificial intelligence: A survey. In 2018 41st International convention on informa- tion and communication technology, electronics and mi- croelectronics (MIPRO), pages 0210-0215. IEEE, 2018.","title":"Explainable artificial intelligence: A survey","authors":"Filip Karlo Došilović, Mario Brčić, Nikica Hlupić","year":"2018","venue":"2018 41st International convention on information and communication technology, electronics and microelectronics (MIPRO)","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Freitas, 2014] Alex A Freitas. Comprehensible classifica- tion models: a position paper. ACM SIGKDD explorations newsletter, 15(1):1-10, 2014.","title":"Comprehensible classification models: a position paper","authors":"Alex A Freitas","year":"2014","venue":"ACM SIGKDD explorations newsletter","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Fu, 1991] LiMin Fu. Rule learning by searching on adapted nets. In AAAI, volume 91, pages 590-595, 1991.","title":"LiMin Fu. Rule learning by searching on adapted nets","authors":"Fu","year":"1991","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Guidotti et al., 2018] Riccardo Guidotti, Anna Monreale, Salvatore Ruggieri, Franco Turini, Fosca Giannotti, and Dino Pedreschi. A survey of methods for explaining black box models. ACM computing surveys (CSUR), 51(5):93, 2018.","title":"A survey of methods for explaining black box models","authors":"Riccardo Guidotti, Anna Monreale, Salvatore Ruggieri, Franco Turini, Fosca Giannotti, Dino Pedreschi","year":"2018","venue":"ACM computing surveys","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Gunning, 2017] David Gunning. Explainable artificial in- telligence (xai). Defense Advanced Research Projects Agency (DARPA), nd Web, 2, 2017.","title":"Defense Advanced Research Projects Agency (DARPA), nd Web","authors":"David Gunning","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Huysmans et al., 2011] Johan Huysmans, Karel Dejaeger, Christophe Mues, Jan Vanthienen, and Bart Baesens. An empirical evaluation of the comprehensibility of decision table, tree and rule based predictive models. Decision Sup- port Systems, 51(1):141-154, 2011.","title":"An empirical evaluation of the comprehensibility of decision table, tree and rule based predictive models","authors":"Johan Huysmans, Karel Dejaeger, Christophe Mues, Jan Vanthienen, Bart Baesens","year":"2011","venue":"Decision Support Systems","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Liu, 2007] Bing Liu. Web data mining: exploring hyper- links, contents, and usage data. Springer Science & Busi- ness Media, 2007.","title":"Web data mining: exploring hyperlinks, contents, and usage data","authors":"Bing Liu, Liu","year":"2007","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Melacci and Belkin, 2011] Stefano Melacci and Mikhail Belkin. Laplacian support vector machines trained in the primal. Journal of Machine Learning Research, 12(Mar):1149-1184, 2011.","title":"Laplacian support vector machines trained in the primal","authors":"Stefano Melacci, Mikhail Belkin","year":"2011","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Melacci and Gori, 2012] Stefano Melacci and Marco Gori. Unsupervised learning by minimal entropy encoding. IEEE transactions on neural networks and learning sys- tems, 23(12):1849-1861, 2012.","title":"Unsupervised learning by minimal entropy encoding","authors":"Stefano Melacci, Marco Gori","year":"2012","venue":"IEEE transactions on neural networks and learning systems","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Melacci et al., 2009] Stefano Melacci, Marco Maggini, and Marco Gori. Semi-supervised learning with constraints for multi-view object recognition. In International Con- ference on Artificial Neural Networks, pages 653-662. Springer, 2009.","title":"Semi-supervised learning with constraints for multi-view object recognition","authors":"Melacci","year":"2009","venue":"International Conference on Artificial Neural Networks","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Molnar, 2019] Christoph Molnar. Interpretable machine learning. Lulu. com, 2019.","title":"Interpretable machine learning","authors":"Christoph Molnar","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Russell and Norvig, 2016] Stuart J Russell and Peter Norvig. Artificial intelligence: a modern approach. Malaysia; Pearson Education Limited,, 2016.","title":"Artificial intelligence: a modern approach","authors":"J Stuart, Peter Russell, Norvig","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Sato and Tsukimoto, 2001] Makoto Sato and Hiroshi Tsukimoto. Rule extraction from neural networks via decision tree induction. In IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No. 01CH37222), volume 3, pages 1870-1875. IEEE, 2001.","title":"Rule extraction from neural networks via decision tree induction","authors":"Tsukimoto Sato, Makoto Sato, Hiroshi Tsukimoto","year":"2001","venue":"IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No. 01CH37222)","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Teso and Kersting, 2019] Stefano Teso and Kristian Kerst- ing. Explanatory interactive machine learning. In Pro- ceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society, pages 239-245, 2019.","title":"Explanatory interactive machine learning","authors":"Kersting Teso, Stefano Teso, Kristian Kersting","year":"2019","venue":"Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Towell and Shavlik, 1993] Geoffrey G Towell and Jude W Shavlik. Extracting refined rules from knowledge-based neural networks. Machine learning, 13(1):71-101, 1993.","title":"Extracting refined rules from knowledge-based neural networks","authors":"G Geoffrey, Jude W Towell, Shavlik","year":"1993","venue":"Machine learning","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Tsukimoto, 2000] Hiroshi Tsukimoto. Extracting rules from trained neural networks. IEEE Transactions on Neu- ral networks, 11(2):377-389, 2000.","title":"Extracting rules from trained neural networks","authors":"Hiroshi Tsukimoto, Tsukimoto","year":"2000","venue":"IEEE Transactions on Neural networks","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Witten and Frank, 2005] Ian H Witten and Eibe Frank. Data mining: Practical machine learning tools and techniques 2nd edition. Morgan Kaufmann, San Francisco, 2005.","title":"Data mining: Practical machine learning tools and techniques 2nd edition","authors":"H Ian, Eibe Witten, Frank","year":"2005","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Zilke et al., 2016] Jan Ruben Zilke, Eneldo Loza Mencía, and Frederik Janssen. Deepred-rule extraction from deep neural networks. In International Conference on Discov- ery Science, pages 457-473. Springer, 2016.","title":"Deepred-rule extraction from deep neural networks","authors":"Zilke","year":"2016","venue":"International Conference on Discovery Science","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}