{"type":"ScholarlyArticle","title":"On Preferred Abductive Explanations for Decision Trees and Random Forests","authors":[{"name":"Gilles Audemard","slug":"gilles-audemard","given":"Gilles","family":"Audemard","affiliation":"Univ. Artois , CNRS , Centre de Recherche en Informatique de Lens (CRIL) , F-62300 Lens , France"},{"name":"Steve Bellart","slug":"steve-bellart","given":"Steve","family":"Bellart","affiliation":"Univ. Artois , CNRS , Centre de Recherche en Informatique de Lens (CRIL) , F-62300 Lens , France"},{"name":"Louenas Bounia","slug":"louenas-bounia","given":"Louenas","family":"Bounia","affiliation":"Univ. Artois , CNRS , Centre de Recherche en Informatique de Lens (CRIL) , F-62300 Lens , France"},{"name":"Frederic Koriche","slug":"frederic-koriche","given":"Frédéric","family":"Koriche","affiliation":"Univ. Artois , CNRS , Centre de Recherche en Informatique de Lens (CRIL) , F-62300 Lens , France"},{"name":"Jean-Marie Lagniez","slug":"jean-marie-lagniez","given":"Jean-Marie","family":"Lagniez","affiliation":"Univ. Artois , CNRS , Centre de Recherche en Informatique de Lens (CRIL) , F-62300 Lens , France"},{"name":"Pierre Marquis","slug":"pierre-marquis","given":"Pierre","family":"Marquis","affiliation":"Univ. Artois , CNRS , Centre de Recherche en Informatique de Lens (CRIL) , F-62300 Lens , France; Institut Universitaire de France {audemard ,"}],"abstract":"Abductive explanations take a central place in eXplainable Artificial Intelligence (XAI) by clarifying with few features \r\nthe way data instances are classified. However, instances may have exponentially many minimum-size abductive explanations, and\r\nthis source of complexity holds even for ``intelligible'' classifiers, such as decision trees. When the number of such abductive explanations is huge,\r\ncomputing one of them, only, is often not informative enough. Especially, better explanations than the one\r\nthat is derived may exist. As a way to circumvent this issue, we propose to leverage \r\na model of the explainee, making precise her / his preferences about explanations, and to compute only \r\npreferred explanations. In this paper, several models are pointed out and discussed. For each model, we present and\r\nevaluate an algorithm for computing preferred majoritary reasons, where majoritary reasons are specific abductive\r\nexplanations suited to random forests. We show that in practice the preferred majoritary reasons for an instance\r\ncan be far less numerous than its majoritary reasons.","doi":"10.24963/ijcai.2022/91","url":"https://ijcai.org/proceedings/2022/91","pdf":"https://ijcai.org/proceedings/2022/0091.pdf","markdown":"https://ijcai.org/proceedings/2022/91.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/91","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":"AI Ethics, Trust, Fairness","track":"Main Track","number":91,"pages":{"first":643,"last":650},"keywords":["AI Ethics, Trust, Fairness: Trustworthy AI","Knowledge Representation and Reasoning: Preference Modelling and Preference-Based Reasoning","AI Ethics, Trust, Fairness: Explainability and Interpretability","Constraint Satisfaction and Optimization: Constraints and Machine Learning"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38987120","length_sec":76,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38985263","length_sec":691,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Adadi and Berrada, 2018] A. Adadi and M. Berrada. Peek- ing inside the black-box: A survey on explainable artificial intelligence (XAI). IEEE Access, 6:52138-52160, 2018.","title":"Peeking inside the black-box: A survey on explainable artificial intelligence (XAI)","authors":"A Adadi, M Berrada","year":"2018","venue":"IEEE Access","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Ansótegui and Gabàs, 2017] C. Ansótegui and J. Gabàs. WPM3: an (in)complete algorithm for weighted partial MaxSAT. Artificial Intelligence, 250:37-57, 2017.","title":"WPM3: an (in)complete algorithm for weighted partial MaxSAT","authors":"C Ansótegui, J Gabàs","year":"2017","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Audemard et al., 2022] G. Audemard, S. Bellart, L. Bounia, F. Koriche, J-M. Lagniez, and P. Marquis. Trading com- plexity for sparsity in random forest explanations. In Proc. of AAAI'22, 2022.","title":"Trading complexity for sparsity in random forest explanations","authors":"G Audemard, S Bellart, L Bounia, F Koriche, J-M Lagniez, P Marquis","year":"2022","venue":"Proc. of AAAI'22","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Breiman et al., 1984] L. Breiman, J. H. Friedman, R. A. Ol- shen, and C. J. Stone. Classification and Regression Trees. Wadsworth, 1984.","title":"Classification and Regression Trees","authors":"L Breiman, J H Friedman, R A Olshen, C J Stone","year":"1984","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Breiman, 2001] L. Breiman. Random forests. Machine Learning, 45(1):5-32, 2001.","title":"Random forests","authors":"L Breiman","year":"2001","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Brewka, 1989] G. Brewka. Preferred subtheories: an ex- tended logical framework for default reasoning. In Proc. of IJCAI'89, pages 1043-1048, 1989.","title":"Preferred subtheories: an extended logical framework for default reasoning","authors":"G Brewka","year":"1989","venue":"Proc. of IJCAI'89","doi":null,"url":null,"internal_url":"/proceedings/1989/167"},{"position":7,"raw":"[Darwiche and Hirth, 2020] A. Darwiche and A. Hirth. On the reasons behind decisions. In Proc. of ECAI'20, pages 712-720, 2020.","title":"On the reasons behind decisions","authors":"Hirth Darwiche, A Darwiche, A Hirth","year":"2020","venue":"Proc. of ECAI'20","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Doshi-Velez and Kim, 2017] F. Doshi-Velez and B. Kim. A roadmap for a rigorous science of interpretability. CoRR, abs/1702.08608, 2017.","title":"A roadmap for a rigorous science of interpretability","authors":"Doshi-Velez, ; ] F Kim, B Doshi-Velez, Kim","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Guidotti et al., 2019] R. Guidotti, A. Monreale, S. Ruggieri, F. Turini, F. Giannotti, and D. Pedreschi. A survey of methods for explaining black box models. ACM Comput- ing Surveys, 51(5):93:1-93:42, 2019.","title":"A survey of methods for explaining black box models","authors":"R Guidotti, A Monreale, S Ruggieri, F Turini, F Giannotti, D Pedreschi","year":"2019","venue":"ACM Computing Surveys","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Huang et al., 2021] X. Huang, Y. Izza, A. Ignatiev, M. C. Cooper, N. Asher, and J. Marques-Silva. Efficient ex- planations for knowledge compilation languages. CoRR, abs/2107.01654, 2021.","title":"Efficient explanations for knowledge compilation languages","authors":"Huang","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Ignatiev et al., 2019] A. Ignatiev, N. Narodytska, and J. Marques-Silva. Abduction-based explanations for ma- chine learning models. In Proc. of AAAI'19, pages 1511- 1519, 2019.","title":"Abduction-based explanations for machine learning models","authors":"A Ignatiev, N Narodytska, J Marques-Silva","year":"2019","venue":"Proc. of AAAI'19","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Ignatiev et al., 2020] A. Ignatiev, N. Narodytska, N. Asher, and J. Marques-Silva. On relating 'why?' and 'why not?' explanations. CoRR, abs/2012.11067, 2020.","title":"On relating 'why?' and 'why not?' explanations","authors":"A Ignatiev, N Narodytska, N Asher, J Marques-Silva","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Ignatiev, 2020] A. Ignatiev. Towards trustable explainable AI. In Proc. of IJCAI'20, pages 5154-5158, 2020.","title":"Towards trustable explainable AI","authors":"A Ignatiev","year":"2020","venue":"Proc. of IJCAI'20","doi":null,"url":null,"internal_url":"/proceedings/2020/726"},{"position":14,"raw":"[Izza and Marques-Silva, 2021] Y. Izza and J. Marques- Silva. On explaining random forests with SAT. In Proc. of IJCAI'21, pages 2584-2591, 2021.","title":"On explaining random forests with SAT","authors":"Y Izza, J Marques-Silva","year":"2021","venue":"Proc. of IJCAI'21","doi":null,"url":null,"internal_url":"/proceedings/2021/356"},{"position":15,"raw":"[Lipton, 2018] Z. C. Lipton. The mythos of model inter- pretability. Communications of the ACM, 61(10):36-43, 2018.","title":"The mythos of model interpretability","authors":"Z C Lipton","year":"2018","venue":"Communications of the ACM","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Lundberg and Lee, 2017] S. Lundberg and S-I. Lee. A uni- fied approach to interpreting model predictions. In Proc. of NIPS'17, pages 4765-4774, 2017.","title":"A unified approach to interpreting model predictions","authors":"S Lundberg, S-I Lee","year":"2017","venue":"Proc. of NIPS'17","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Lundberg et al., 2020] S. M. Lundberg, G. G. Erion, H. Chen, A. J. DeGrave, J. M. Prutkin, B. Nair, R. Katz, J. Himmelfarb, N. Bansal, and S. Lee. From local explana- tions to global understanding with explainable AI for trees. Nat. Mach. Intell., 2(1):56-67, 2020.","title":"From local explanations to global understanding with explainable AI for trees","authors":"S M Lundberg, G G Erion, H Chen, A J Degrave, J M Prutkin, B Nair, R Katz, J Himmelfarb, N Bansal, S Lee","year":"2020","venue":"Nat. Mach. Intell","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Martins et al., 2014] R. Martins, V. M. Manquinho, and I. Lynce. Open-WBO: A modular MaxSAT solver. In Proc. of SAT'14, pages 438-445, 2014.","title":"Open-WBO: A modular MaxSAT solver","authors":"R Martins, V M Manquinho, I Lynce","year":"2014","venue":"Proc. of SAT'14","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Miller, 2019] T. Miller. Explanation in artificial intelli- gence: Insights from the social sciences. Artificial Intelli- gence, 267:1-38, 2019.","title":"Explanation in artificial intelligence: Insights from the social sciences","authors":"T Miller","year":"2019","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Molnar, 2020] C. Molnar. Interpretable Machine Learning. Leanpub, 2020.","title":"Interpretable Machine Learning","authors":"C Molnar","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Narayanan et al., 2018] M. Narayanan, E. Chen, J. He, B. Kim, S. Gershman, and F. Doshi-Velez. How do hu- mans understand explanations from machine learning sys- tems? an evaluation of the human-interpretability of ex- planation. CoRR, abs/1802.00682, 2018.","title":"How do humans understand explanations from machine learning systems? an evaluation of the human-interpretability of explanation","authors":"M Narayanan, E Chen, J He, B Kim, S Gershman, F Doshi-Velez","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Pedregosa et al., 2011] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blon- del, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825-2830, 2011.","title":"Scikit-learn: Machine learning in Python","authors":"F Pedregosa, G Varoquaux, A Gramfort, V Michel, B Thirion, O Grisel, M Blondel, P Prettenhofer, R Weiss, V Dubourg, J Vanderplas, A Passos, D Cournapeau, M Brucher, M Perrot, E Duchesnay","year":"2011","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Quinlan, 1986] J. R. Quinlan. Induction of decision trees. Machine Learning, 1(1):81-106, 1986.","title":"Induction of decision trees","authors":"J R Quinlan","year":"1986","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Ribeiro et al., 2016] M. T. Ribeiro, S. Singh, and C. Guestrin. \"why should I trust you?\": Explaining the predictions of any classifier. In Proc. of SIGKDD'16, pages 1135-1144, 2016.","title":"why should I trust you?\": Explaining the predictions of any classifier","authors":"M T Ribeiro, S Singh, C Guestrin","year":"2016","venue":"Proc. of SIGKDD'16","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Ribeiro et al., 2018] M. T. Ribeiro, S. Singh, and C. Guestrin. Anchors: High-precision model-agnostic explanations. In Proc. of AAAI'18, pages 1527-1535, 2018.","title":"Anchors: High-precision model-agnostic explanations","authors":"M T Ribeiro, S Singh, C Guestrin","year":"2018","venue":"Proc. of AAAI'18","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Samek et al., 2019] W. Samek, G. Montavon, A. Vedaldi, L.K. Hansen, and K.R. Müller. Explainable AI: Interpret- ing, Explaining and Visualizing Deep Learning. Springer, 2019.","title":"Explainable AI: Interpreting, Explaining and Visualizing Deep Learning","authors":"W Samek, G Montavon, A Vedaldi, L K Hansen, K R Müller","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Shih et al., 2018] A. Shih, A. Choi, and A. Darwiche. A symbolic approach to explaining bayesian network classi- fiers. In Proc. of IJCAI'18, pages 5103-5111, 2018.","title":"A symbolic approach to explaining bayesian network classifiers","authors":"A Shih, A Choi, A Darwiche","year":"2018","venue":"Proc. of IJCAI'18","doi":null,"url":null,"internal_url":"/proceedings/2018/708"},{"position":28,"raw":"[Srinivasan and Chander, 2020] R. Srinivasan and A. Chan- der. Explanation perspectives from the cognitive sciences -A survey. In Proc. of IJCAI'20, pages 4812-4818, 2020.","title":"Explanation perspectives from the cognitive sciences -A survey","authors":"R Srinivasan, A Chander","year":"2020","venue":"Proc. of IJCAI'20","doi":null,"url":null,"internal_url":"/proceedings/2020/670"},{"position":29,"raw":"[Xu et al., 2019] F. Xu, H. Uszkoreit, Y. Du, W. Fan, D. Zhao, and J. Zhu. Explainable AI: A brief survey on his- tory, research areas, approaches and challenges. In Proc. of NLPCC'19, pages 563-574, 2019.","title":"Explainable AI: A brief survey on history, research areas, approaches and challenges","authors":"F Xu, H Uszkoreit, Y Du, W Fan, D Zhao, J Zhu","year":"2019","venue":"Proc. of NLPCC'19","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}