{"type":"ScholarlyArticle","title":"Deriving Provably Correct Explanations for Decision Trees: The Impact of Domain Theories","authors":[{"name":"Gilles Audemard","slug":"gilles-audemard","given":"Gilles","family":"Audemard","affiliation":"Univ. Artois , CNRS , CRIL , F-62300 Lens , France"},{"name":"Jean-Marie Lagniez","slug":"jean-marie-lagniez","given":"Jean-Marie","family":"Lagniez","affiliation":"Univ. Artois , CNRS , CRIL , F-62300 Lens , France"},{"name":"Pierre Marquis","slug":"pierre-marquis","given":"Pierre","family":"Marquis","affiliation":"Univ. Artois , CNRS , CRIL , F-62300 Lens , France; Institut Universitaire de France {audemard ,"},{"name":"Nicolas Szczepanski","slug":"nicolas-szczepanski","given":"Nicolas","family":"Szczepanski","affiliation":"Univ. Artois , CNRS , CRIL , F-62300 Lens , France"}],"abstract":"We are interested in identifying the complexity of computing local explanations of various types given a decision tree, when the Boolean conditions used in the tree are not independent. This is usually the case when decision trees are learned from instances described using numerical or categorical attributes. In such a case, considering the domain theory indicating how the Boolean conditions occurring in the tree are logically connected is paramount to derive provably correct explanations. However, the nature of the domain theory may have a strong impact on the complexity of generating explanations. In this paper, we identify the complexity of deriving local explanations (abductive or contrastive) given a decision tree in the general case, and under several natural restrictions about the domain theory.","doi":"10.24963/ijcai.2024/408","url":"https://ijcai.org/proceedings/2024/408","pdf":"https://ijcai.org/proceedings/2024/0408.pdf","markdown":"https://ijcai.org/proceedings/2024/408.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/408","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Machine Learning","track":"Main Track","number":408,"pages":{"first":3688,"last":3696},"keywords":["Machine Learning: ML: Explainable/Interpretable machine learning","Knowledge Representation and Reasoning: KRR: Computational complexity of reasoning"],"videos":[],"references":[{"position":1,"raw":"[Aspvall et al., 1979] B. Aspvall, M. Plass, and R. Tarjan. A linear-time algorithm for testing the truth of certain quan- tified Boolean formulas. Information Processing Letters, 8:121-123, 1979. Erratum: Information Processing Let- ters 14(4): 195 (1982).","title":"A linear-time algorithm for testing the truth of certain quantified Boolean formulas","authors":"B Aspvall, M Plass, R Tarjan","year":"1979","venue":"Erratum: Information Processing Letters","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Audemard et al., 2021] G. Audemard, S. Bellart, L. Bounia, F. Koriche, J.-M. Lagniez, and P. Marquis. On the compu- tational intelligibility of boolean classifiers. In Proc. of KR'21, pages 74-86, 2021.","title":"On the computational intelligibility of boolean classifiers","authors":"G Audemard, S Bellart, L Bounia, F Koriche, J.-M Lagniez, P Marquis","year":"2021","venue":"Proc. of KR'21","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Audemard et al., 2022a] G. Audemard, S. Bellart, L. Bou- nia, F. Koriche, J.-M. Lagniez, and P. Marquis. On pre- ferred abductive explanations for decision trees and ran- dom forests. In Proc. of IJCAI'22, pages 643-650, 2022.","title":"On preferred abductive explanations for decision trees and random forests","authors":"Audemard","year":"2022","venue":"Proc. of IJCAI'22","doi":null,"url":null,"internal_url":"/proceedings/2022/91"},{"position":4,"raw":"[Audemard et al., 2022b] G. Audemard, S. Bellart, L. Bou- nia, F. Koriche, J.-M. Lagniez, and P. Marquis. On the explanatory power of boolean decision trees. Data Knowl. Eng., 142:102088, 2022.","title":"On the explanatory power of boolean decision trees","authors":"Audemard","year":"2022","venue":"Data Knowl. Eng","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Audemard et al., 2023] G. Audemard, J.-M. Lagniez, P. Marquis, and N. Szczepanski. On contrastive explana- tions for tree-based classifiers. In Proc. of ECAI'23, pages 117-124, 2023.","title":"On contrastive explanations for tree-based classifiers","authors":"G Audemard, J.-M Lagniez, P Marquis, N Szczepanski","year":"2023","venue":"Proc. of ECAI'23","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Barceló et al., 2020] P. Barceló, M. Monet, J. Pérez, and B. Subercaseaux. Model interpretability through the lens of computational complexity. In Proc. of NeurIPS'20, 2020.","title":"Model interpretability through the lens of computational complexity","authors":"P Barceló, M Monet, J Pérez, B Subercaseaux","year":"2020","venue":"Proc. of NeurIPS'20","doi":null,"url":null,"internal_url":null},{"position":7,"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":8,"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":9,"raw":"[Cooper and Amgoud, 2023] M.C. Cooper and L. Amgoud. Abductive explanations of classifiers under constraints: Complexity and properties. In Proc. of ECAI'23, pages 469-476, 2023.","title":"Abductive explanations of classifiers under constraints: Complexity and properties","authors":"M C Cooper, L Amgoud","year":"2023","venue":"Proc. of ECAI'23","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Cooper and Marques-Silva, 2023] M.C. Cooper and J. Marques-Silva. Tractability of explaining classifier decisions. Artif. Intell., 316:103841, 2023.","title":"Tractability of explaining classifier decisions","authors":"M C Cooper, J Marques-Silva","year":"2023","venue":"Artif. Intell","doi":null,"url":null,"internal_url":null},{"position":11,"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":12,"raw":"[Darwiche and Ji, 2022] A. Darwiche and C. Ji. On the com- putation of necessary and sufficient explanations. In Proc. of AAAI'22, pages 5582-5591, 2022.","title":"On the computation of necessary and sufficient explanations","authors":"A Darwiche, C Ji","year":"2022","venue":"Proc. of AAAI'22","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Darwiche and Marquis, 2002] A. Darwiche and P. Marquis. A knowledge compilation map. Journal of Artificial Intel- ligence Research, 17:229-264, 2002.","title":"A knowledge compilation map","authors":"Marquis ; Darwiche, A Darwiche, P Marquis","year":"2002","venue":"Journal of Artificial Intelligence Research","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[de Colnet and Marquis, 2022] A. de Colnet and P. Marquis. On the complexity of enumerating prime implicants from decision-dnnf circuits. In Proc. of IJCAI'22, pages 2583- 2590, 2022.","title":"On the complexity of enumerating prime implicants from decision-dnnf circuits","authors":"A De Colnet, P Marquis","year":"2022","venue":"Proc. of IJCAI'22","doi":null,"url":null,"internal_url":"/proceedings/2022/358"},{"position":15,"raw":"[Even et al., 1976] S. Even, A. Itai, and A. Shamir. On the complexity of timetable and integral multi-commodity flow problems. SIAM J. on Comp, 5(4):691-703, 1976.","title":"On the complexity of timetable and integral multi-commodity flow problems","authors":"S Even, A Itai, A Shamir","year":"1976","venue":"SIAM J. on Comp","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Freund and Schapire, 1997] Y. Freund and R.E. Schapire. A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci., 55(1):119-139, 1997.","title":"A decision-theoretic generalization of on-line learning and an application to boosting","authors":"Y Freund, R E Schapire","year":"1997","venue":"J. Comput. Syst. Sci","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Friedman, 2001] J. H. Friedman. Greedy function approxi- mation: A gradient boosted machine. The Annals of Statis- tics, 29(5):1189-1232, 2001.","title":"Greedy function approximation: A gradient boosted machine","authors":"J H Friedman","year":"2001","venue":"The Annals of Statistics","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Gorji and Rubin, 2022] N. Gorji and S. Rubin. Sufficient reasons for classifier decisions in the presence of domain constraints. In Proc. of AAAI'22, pages 5660-5667, 2022.","title":"Sufficient reasons for classifier decisions in the presence of domain constraints","authors":"N Gorji, S Rubin","year":"2022","venue":"Proc. of AAAI'22","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Gunning, 2019] D. Gunning. DARPA's explainable artifi- cial intelligence (XAI) program. In Proc. of IUI'19, 2019.","title":"DARPA's explainable artificial intelligence (XAI) program","authors":"D Gunning","year":"2019","venue":"Proc. of IUI'19","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Huang et al., 2021] X. Huang, Y. Izza, A. Ignatiev, and J. Marques-Silva. On efficiently explaining graph-based classifiers. In Proc. of KR'21, pages 356-367, 2021.","title":"On efficiently explaining graph-based classifiers","authors":"Huang","year":"2021","venue":"Proc. of KR'21","doi":null,"url":null,"internal_url":null},{"position":21,"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":22,"raw":"[Ignatiev et al., 2020a] A. Ignatiev, N. Narodytska, N. Asher, and J. Marques-Silva. From contrastive to abductive explanations and back again. In Proc. of AIxIA'20, pages 335-355, 2020.","title":"From contrastive to abductive explanations and back again","authors":"Ignatiev","year":"2020","venue":"Proc. of AIxIA'20","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Ignatiev et al., 2020b] Alexey Ignatiev, Nina Narodytska, Nicholas Asher, and João Marques-Silva. On relat- ing 'why?' and 'why not?' explanations. CoRR, abs/2012.11067, 2020.","title":"On relating 'why?' and 'why not?' explanations","authors":"Ignatiev","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Izza et al., 2020] Y. Izza, A. Ignatiev, and J. Marques-Silva. On explaining decision trees. CoRR, abs/2010.11034, 2020.","title":"On explaining decision trees","authors":"Y Izza, A Ignatiev, J Marques-Silva","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Izza et al., 2022] Y. Izza, A. Ignatiev, and J. Marques-Silva. On tackling explanation redundancy in decision trees. J. Artif. Intell. Res., 75:261-321, 2022.","title":"On tackling explanation redundancy in decision trees","authors":"Y Izza, A Ignatiev, J Marques-Silva","year":"2022","venue":"J. Artif. Intell. Res","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Marques-Silva, 2023] J. Marques-Silva. Disproving XAI myths with formal methods -initial results. CoRR, abs/2306.01744, 2023.","title":"Disproving XAI myths with formal methods -initial results","authors":"J Marques-Silva","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"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":28,"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":29,"raw":"[Ras et al., 2022] G. Ras, N. Xie, M. van Gerven, and D. Do- ran. Explainable deep learning: A field guide for the unini- tiated. J. Artif. Intell. Res., 73:329-396, 2022.","title":"Explainable deep learning: A field guide for the uninitiated","authors":"G Ras, N Xie, M Van Gerven, D Doran","year":"2022","venue":"J. Artif. Intell. Res","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Schapire and Freund, 2014] R.E. Schapire and Y. Freund. Boosting: Foundations and Algorithms. MIT Press, 2014.","title":"Boosting: Foundations and Algorithms","authors":"R E Schapire, Y Freund","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":31,"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":32,"raw":"[Yang et al., 2019] F. Yang, M. Du, and X. Hu. Evaluating explanation without ground truth in interpretable machine learning. CoRR, abs/1907.06831, 2019.","title":"Evaluating explanation without ground truth in interpretable machine learning","authors":"F Yang, M Du, X Hu","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Yu et al., 2022] J. Yu, A. Ignatiev, P.J. Stuckey, N. Narodyt- ska, and J. Marques-Silva. Eliminating the impossible, whatever remains must be true. CoRR, abs/2206.09551, 2022.","title":"Eliminating the impossible, whatever remains must be true","authors":"J Yu, A Ignatiev, P J Stuckey, N Narodytska, J Marques-Silva","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}