{"type":"ScholarlyArticle","title":"Towards Trustable Explainable AI","authors":[{"name":"Alexey Ignatiev","slug":"alexey-ignatiev","given":"Alexey","family":"Ignatiev","affiliation":"Monash University , Australia"}],"abstract":"Explainable artificial intelligence (XAI) represents arguably one of the most crucial challenges being faced by the area of AI these days. Although the majority of approaches to XAI are of heuristic nature, recent work proposed the use of abductive reasoning to computing provably correct explanations for machine learning (ML) predictions. The proposed rigorous approach was shown to be useful not only for computing trustable explanations but also for validating explanations computed heuristically. It was also applied to uncover a close relationship between XAI and verification of ML models. This paper overviews the advances of the rigorous logic-based approach to XAI and argues that it is indispensable if trustable XAI is of concern.","doi":"10.24963/ijcai.2020/726","url":"https://ijcai.org/proceedings/2020/726","pdf":"https://ijcai.org/proceedings/2020/0726.pdf","markdown":"https://ijcai.org/proceedings/2020/726.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/726","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":"Early Career","track":"Early Career","number":726,"pages":{"first":5154,"last":5158},"keywords":["Multidisciplinary Topics and Applications: Validation and Verification","Machine Learning: Explainable Machine Learning","Machine Learning: Classification","Constraints and SAT: Constraints and Data Mining ; Constraints and Machine Learning"],"videos":[],"references":[{"position":1,"raw":"[ACM, 2018] ACM. Fathers of the deep learning revolution receive ACM A.M. Turing award. http://tiny.cc/9plzpz, 2018.","title":"ACM. Fathers of the deep learning revolution receive ACM A.M. Turing award","authors":null,"year":"2018","venue":null,"doi":null,"url":"http://tiny.cc/9plzpz,2018","internal_url":null},{"position":2,"raw":"[Angwin et al., 2016] Julia Angwin, Jeff Larson, Surya Mattu, and Lauren Kirchner. Machine bias. http://tiny.cc/dd7mjz, 2016.","title":"Machine bias","authors":"Julia Angwin, Jeff Larson, Surya Mattu, Lauren Kirchner","year":null,"venue":null,"doi":null,"url":"http://tiny.cc/dd7mjz,2016","internal_url":null},{"position":3,"raw":"[Baehrens et al., 2010] David Baehrens, Timon Schroeter, Stefan Harmeling, Motoaki Kawanabe, Katja Hansen, and Klaus-Robert Müller. How to explain individual classification decisions. Jour- nal of Machine Learning Research, 11:1803-1831, 2010.","title":"How to explain individual classification decisions","authors":"David Baehrens, Timon Schroeter, Stefan Harmeling, Motoaki Kawanabe, Katja Hansen, Klaus-Robert Müller","year":"2010","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[CACM Letters to the Editor, 2019] CACM Letters to the Editor. A case against mission-critical applications of machine learning. Commun. ACM, 62(8):9, 2019.","title":"CACM Letters to the Editor. A case against mission-critical applications of machine learning","authors":null,"year":"2019","venue":"Commun. ACM","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chalasani et al., 2018] Prasad Chalasani, Somesh Jha, Aravind Sadagopan, and Xi Wu. Adversarial learning and explainability in structured datasets. CoRR, abs/1810.06583, 2018.","title":"Adversarial learning and explainability in structured datasets","authors":"Prasad Chalasani, Somesh Jha, Aravind Sadagopan, Xi Wu","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chen and Guestrin, 2016] Tianqi Chen and Carlos Guestrin. XG- Boost: A scalable tree boosting system. In KDD, pages 785-794, 2016.","title":"XG-Boost: A scalable tree boosting system","authors":"Tianqi Chen, Carlos Guestrin","year":"2016","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Goodfellow et al., 2015] Ian J. Goodfellow, Jonathon Shlens, and Christian Szegedy. Explaining and harnessing adversarial exam- ples. In ICLR (Poster), 2015.","title":"Explaining and harnessing adversarial examples","authors":"Ian J Goodfellow, Jonathon Shlens, Christian Szegedy","year":"2015","venue":"ICLR (Poster)","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Guidotti et al., 2019] Riccardo Guidotti, Anna Monreale, Salva- tore Ruggieri, Franco Turini, Fosca Giannotti, and Dino Pe- dreschi. A survey of methods for explaining black box models. ACM Comput. Surv., 51(5):93:1-93:42, 2019.","title":"A survey of methods for explaining black box models","authors":"Riccardo Guidotti, Anna Monreale, Salvatore Ruggieri, Franco Turini, Fosca Giannotti, Dino Pedreschi","year":"2019","venue":"ACM Comput. Surv","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hubara et al., 2016] Itay Hubara, Matthieu Courbariaux, Daniel Soudry, Ran El-Yaniv, and Yoshua Bengio. Binarized neural net- works. In NIPS, pages 4107-4115, 2016.","title":"Binarized neural networks","authors":"Itay Hubara, Matthieu Courbariaux, Daniel Soudry, Ran El-Yaniv, Yoshua Bengio","year":"2016","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Ignatiev et al., 2016] Alexey Ignatiev, Antonio Morgado, and Joao Marques-Silva. Propositional abduction with implicit hitting sets. In ECAI, pages 1327-1335, 2016.","title":"Propositional abduction with implicit hitting sets","authors":"Alexey Ignatiev, Antonio Morgado, Joao Marques-Silva","year":"2016","venue":"ECAI","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Ignatiev et al., 2018] Alexey Ignatiev, Filipe Pereira, Nina Naro- dytska, and Joao Marques-Silva. A SAT-based approach to learn explainable decision sets. In IJCAR, pages 627-645, 2018.","title":"A SAT-based approach to learn explainable decision sets","authors":"Alexey Ignatiev, Filipe Pereira, Nina Narodytska, Joao Marques-Silva","year":"2018","venue":"IJCAR","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Ignatiev et al., 2019a] Alexey Ignatiev, Nina Narodytska, and Joao Marques-Silva. Abduction-based explanations for machine learn- ing models. In AAAI, pages 1511-1519, 2019.","title":"Abduction-based explanations for machine learning models","authors":"Ignatiev","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Ignatiev et al., 2019b] Alexey Ignatiev, Nina Narodytska, and Joao Marques-Silva. On relating explanations and adversarial exam- ples. In NeurIPS, pages 15857-15867, 2019.","title":"On relating explanations and adversarial examples","authors":"Ignatiev","year":"2019","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Ignatiev et al., 2019c] Alexey Ignatiev, Nina Narodytska, and Joao Marques-Silva. On validating, repairing and refining heuristic ML explanations. CoRR, abs/1907.02509, 2019.","title":"On validating, repairing and refining heuristic ML explanations","authors":"Ignatiev","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Jordan and Mitchell, 2015] Michael I Jordan and Tom M Mitchell. Machine learning: Trends, perspectives, and prospects. Science, 349(6245):255-260, 2015.","title":"Machine learning: Trends, perspectives, and prospects","authors":"I Michael, Tom M Jordan, Mitchell","year":"2015","venue":"Science","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Katz et al., 2017] Guy Katz, Clark W. Barrett, David L. Dill, Kyle Julian, and Mykel J. Kochenderfer. Reluplex: An efficient SMT solver for verifying deep neural networks. In CAV, pages 97-117, 2017.","title":"Reluplex: An efficient SMT solver for verifying deep neural networks","authors":"Guy Katz, Clark W Barrett, David L Dill, Kyle Julian, Mykel J Kochenderfer","year":"2017","venue":"CAV","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[LeCun et al., 2015] Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. Deep learning. Nature, 521(7553):436, 2015.","title":"Deep learning","authors":"Yann Lecun, Yoshua Bengio, Geoffrey Hinton","year":"2015","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Li et al., 2018] Oscar Li, Hao Liu, Chaofan Chen, and Cynthia Rudin. Deep learning for case-based reasoning through proto- types: A neural network that explains its predictions. In AAAI, pages 3530-3537, 2018.","title":"Deep learning for case-based reasoning through prototypes: A neural network that explains its predictions","authors":"Oscar Li, Hao Liu, Chaofan Chen, Cynthia Rudin","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Lundberg and Lee, 2017] Scott M. Lundberg and Su-In Lee. A unified approach to interpreting model predictions. In NIPS, pages 4765-4774, 2017.","title":"A unified approach to interpreting model predictions","authors":"M Scott, Su-In Lundberg, Lee","year":"2017","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Mnih et al., 2015] Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A Rusu, Joel Veness, Marc G Bellemare, Alex Graves, Martin Riedmiller, Andreas K Fidjeland, Georg Ostro- vski, et al. Human-level control through deep reinforcement learning. Nature, 518(7540):529, 2015.","title":"Human-level control through deep reinforcement learning","authors":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A Rusu, Joel Veness, Marc G Bellemare, Alex Graves, Martin Riedmiller, Andreas K Fidjeland, Georg Ostrovski","year":"2015","venue":"Nature","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Monroe, 2018] Don Monroe. AI, explain yourself. Commun. ACM, 61(11):11-13, 2018.","title":"AI, explain yourself","authors":"Don Monroe","year":"2018","venue":"Commun. ACM","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Narodytska et al., 2018a] Nina Narodytska, Alexey Ignatiev, Fil- ipe Pereira, and Joao Marques-Silva. Learning optimal decision trees with SAT. In IJCAI, pages 1362-1368, 2018.","title":"Learning optimal decision trees with SAT","authors":"Narodytska","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/189"},{"position":23,"raw":"[Narodytska et al., 2018b] Nina Narodytska, Shiva Prasad Ka- siviswanathan, Leonid Ryzhyk, Mooly Sagiv, and Toby Walsh. Verifying properties of binarized deep neural networks. In AAAI, 2018.","title":"Verifying properties of binarized deep neural networks","authors":"Narodytska","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Narodytska et al., 2019] Nina Narodytska, Aditya A. Shrotri, Kuldeep S. Meel, Alexey Ignatiev, and Joao Marques-Silva. Assessing heuristic machine learning explanations with model counting. In SAT, pages 267-278, 2019.","title":"Assessing heuristic machine learning explanations with model counting","authors":"Nina Narodytska, Aditya A Shrotri, Kuldeep S Meel, Alexey Ignatiev, Joao Marques-Silva","year":"2019","venue":"SAT","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Narodytska, 2018] Nina Narodytska. Formal analysis of deep bi- narized neural networks. In IJCAI, pages 5692-5696, 2018.","title":"Formal analysis of deep binarized neural networks","authors":"Nina Narodytska","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/811"},{"position":26,"raw":"[Reiter, 1987] Raymond Reiter. A theory of diagnosis from first principles. Artif. Intell., 32(1):57-95, 1987.","title":"A theory of diagnosis from first principles","authors":"Raymond Reiter","year":"1987","venue":"Artif. Intell","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Ribeiro et al., 2016] Marco Túlio Ribeiro, Sameer Singh, and Car- los Guestrin. \"Why should I trust you?\": Explaining the predic- tions of any classifier. In KDD, pages 1135-1144, 2016.","title":"Why should I trust you?\": Explaining the predictions of any classifier","authors":"Marco Túlio Ribeiro, Sameer Singh, Carlos Guestrin","year":"2016","venue":"KDD","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Ribeiro et al., 2018] Marco Túlio Ribeiro, Sameer Singh, and Car- los Guestrin. Anchors: High-precision model-agnostic explana- tions. In AAAI, 2018.","title":"Anchors: High-precision model-agnostic explanations","authors":"Marco Túlio Ribeiro, Sameer Singh, Carlos Guestrin","year":"2018","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Ruan et al., 2018] Wenjie Ruan, Xiaowei Huang, and Marta Kwiatkowska. Reachability analysis of deep neural networks with provable guarantees. In IJCAI, pages 2651-2659, 2018.","title":"Reachability analysis of deep neural networks with provable guarantees","authors":"Wenjie Ruan, Xiaowei Huang, Marta Kwiatkowska","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/368"},{"position":30,"raw":"[Rymon, 1994] Ron Rymon. An SE-tree-based prime implicant generation algorithm. Ann. Math. Artif. Intell., 11(1-4):351-366, 1994.","title":"An SE-tree-based prime implicant generation algorithm","authors":"Ron Rymon","year":"1994","venue":"Ann. Math. Artif. Intell","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Shih et al., 2018] Andy Shih, Arthur Choi, and Adnan Darwiche. A symbolic approach to explaining bayesian network classifiers. In IJCAI, pages 5103-5111, 2018.","title":"A symbolic approach to explaining bayesian network classifiers","authors":"Andy Shih, Arthur Choi, Adnan Darwiche","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/708"},{"position":32,"raw":"[Soos and Meel, 2019] Mate Soos and Kuldeep S. Meel. BIRD: En- gineering an efficient CNF-XOR SAT solver and its applications to approximate model counting. In AAAI, 2019.","title":"BIRD: Engineering an efficient CNF-XOR SAT solver and its applications to approximate model counting","authors":"Meel ; ] Mate Soos, Kuldeep S Soos, Meel","year":"2019","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Szegedy et al., 2014] Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian J. Goodfellow, and Rob Fergus. Intriguing properties of neural networks. In ICLR (Poster), 2014.","title":"Intriguing properties of neural networks","authors":"Szegedy","year":"2014","venue":"ICLR (Poster)","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Tao et al., 2018] Guanhong Tao, Shiqing Ma, Yingqi Liu, and Xi- angyu Zhang. Attacks meet interpretability: Attribute-steered de- tection of adversarial samples. In NeurIPS, pages 7728-7739, 2018.","title":"Attacks meet interpretability: Attribute-steered detection of adversarial samples","authors":"Tao","year":"2018","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Weld and Bansal, 2019] Daniel S. Weld and Gagan Bansal. The challenge of crafting intelligible intelligence. Commun. ACM, 62(6):70-79, 2019.","title":"The challenge of crafting intelligible intelligence","authors":"Daniel S Weld, Gagan Bansal","year":"2019","venue":"Commun. ACM","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Zhou and Sun, 2019] Zhi Quan Zhou and Liqun Sun. Metamor- phic testing of driverless cars. Commun. ACM, 62(3):61-67, 2019.","title":"Metamorphic testing of driverless cars","authors":"Zhi Quan, Zhou, Liqun Sun","year":"2019","venue":"Commun. ACM","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}