{"type":"ScholarlyArticle","title":"Computing Abductive Explanations for Boosted Regression Trees","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":"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":"We present two algorithms for generating (resp. evaluating) abductive explanations for boosted regression trees. Given an instance x and an interval I containing its value F (x) for the boosted regression tree F at hand, the generation algorithm returns a (most general) term t over the Boolean conditions in F such that every instance x′ satisfying t is such that F (x′ ) ∈ I. The evaluation algorithm tackles the corresponding inverse problem: given F , x and a term t over the Boolean conditions in F such that t covers x, find the least interval I_t such that for every instance x′ covered by t we have F (x′ ) ∈ I_t . Experiments on various datasets show that the two algorithms are practical enough to be used for generating (resp. evaluating) abductive explanations for boosted regression trees based on a large number of Boolean conditions.","doi":"10.24963/ijcai.2023/382","url":"https://ijcai.org/proceedings/2023/382","pdf":"https://ijcai.org/proceedings/2023/0382.pdf","markdown":"https://ijcai.org/proceedings/2023/382.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/382","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Machine Learning","track":"Main Track","number":382,"pages":{"first":3432,"last":3441},"keywords":["Machine Learning: ML: Explainable/Interpretable machine learning","Constraint Satisfaction and Optimization: CSO: Constraint programming","Machine Learning: ML: Regression"],"videos":[],"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":"[Arrieta et al., 2020] A. Barredo Arrieta, N. Díaz R., J. Del Ser, A. Bennetot, S. Tabik, A. Barbado, S. García, S. Gil- Lopez, D. Molina, R. Benjamins, R. Chatila, and F. Her- rera. Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward respon- sible AI. Inf. Fusion, 58:82-115, 2020.","title":"Explainable artificial intelligence (XAI): concepts, taxonomies, opportunities and challenges toward responsible AI","authors":"A Barredo Arrieta, N Díaz, R, J Del, A Ser, S Bennetot, A Tabik, S Barbado, S García, D Gil-Lopez, R Molina, R Benjamins, F Chatila","year":"2020","venue":"Inf. Fusion","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, pages 5461-5469, 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":"[Audemard et al., 2023] G. Audemard, J.-M. Lagniez, P. Marquis, and N. Szczepanski. Computing abductive explanations for boosted trees. In Proc. of the 26th International Conference on Artificial Intelligence and Statistics, AISTATS'23, volume 206 of Proce. of Machine Learning Research, pages 4699-4711, 2023.","title":"Computing abductive explanations for boosted trees","authors":"G Audemard, J.-M Lagniez, P Marquis, N Szczepanski","year":"2023","venue":"Proc. of the 26th International Conference on Artificial Intelligence and Statistics, AISTATS'23","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Barber et al., 2021] Rina Foygel Barber, Emmanuel J. Candès, Aaditya Ramdas, and Ryan J. Tibshirani. Predic- tive inference with the jackknife+. The Annals of Statistics, 49(1):486-507, 2021.","title":"Predictive inference with the jackknife+","authors":"Rina Foygel Barber, Emmanuel J Candès, Aaditya Ramdas, Ryan J Tibshirani","year":"2021","venue":"The Annals of Statistics","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Caruana et al., 2020] R. Caruana, S. M. Lundberg, M. Túlio Ribeiro, H. Nori, and S. Jenkins. Intelligible and explain- able machine learning: Best practices and practical chal- lenges. In Proc. of KDD'20, pages 3511-3512. ACM, 2020.","title":"Intelligible and explainable machine learning: Best practices and practical challenges","authors":"R Caruana, S M Lundberg, M Túlio Ribeiro, H Nori, S Jenkins","year":"2020","venue":"Proc. of KDD'20","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Chen and Guestrin, 2016] T. Chen and C. Guestrin. XG- Boost: A scalable tree boosting system. In Proc. of KDD'16, page 785-794, 2016.","title":"XG-Boost: A scalable tree boosting system","authors":"T Chen, C Guestrin","year":"2016","venue":"Proc. of KDD'16","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Choi et al., 2020] A. Choi, A. Shih, A. Goyanka, and A. Darwiche. On symbolically encoding the behavior of random forests. In Proc. of FoMLAS'20, 3rd Workshop on Formal Methods for ML-Enabled Autonomous Systems, Workshop at CAV'20, 2020.","title":"On symbolically encoding the behavior of random forests","authors":"A Choi, A Shih, A Goyanka, A Darwiche","year":"2020","venue":"Proc. of FoMLAS'20, 3rd Workshop on Formal Methods for ML-Enabled Autonomous Systems, Workshop at CAV'20","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Cplex, 2009] IBM ILOG Cplex. V12. 1: User's manual for cplex. International Business Machines Corporation, 46(53):157, 2009.","title":"IBM ILOG Cplex. V12. 1: User's manual for cplex","authors":"Cplex","year":"2009","venue":"International Business Machines Corporation","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Cui et al., 2015] Z. Cui, W. Chen, Y. He, and Y. Chen. Opti- mal action extraction for random forests and boosted trees. In Proc. of KDD'15, pages 179-188, 2015.","title":"Optimal action extraction for random forests and boosted trees","authors":"Z Cui, W Chen, Y He, Y Chen","year":"2015","venue":"Proc. of KDD'15","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":"[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":13,"raw":"[Even et al., 1976] S. Even, A. Itai, and A. Shamir. On the complexity of timetable and multicommodity flow prob- lems. SIAM J. Comput., 5(4):691-703, 1976.","title":"On the complexity of timetable and multicommodity flow problems","authors":"S Even, A Itai, A Shamir","year":"1976","venue":"SIAM J. Comput","doi":null,"url":null,"internal_url":null},{"position":14,"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":15,"raw":"[Hada and Carreira-Perpiñán, 2021] S.S. Hada and M. Carreira-Perpiñán. Exploring counterfactual ex- planations for classification and regression trees. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pages 489-504, 2021.","title":"Exploring counterfactual explanations for classification and regression trees","authors":"S S Hada, M Carreira-Perpiñán","year":"2021","venue":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Ignatiev et al., 2019a] 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":"Ignatiev","year":"2019","venue":"Proc. of AAAI'19","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Ignatiev et al., 2019b] A. Ignatiev, N. Narodytska, and J. 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":18,"raw":"[Ignatiev et al., 2022] A. Ignatiev, Y. Izza, P.J. Stuckey, and J. Marques-Silva. Using MaxSAT for efficient explana- tions of tree ensembles. In Proc. of AAAI'22, pages 3776- 3785, 2022.","title":"Using MaxSAT for efficient explanations of tree ensembles","authors":"A Ignatiev, Y Izza, P J Stuckey, J Marques-Silva","year":"2022","venue":"Proc. of AAAI'22","doi":null,"url":null,"internal_url":null},{"position":19,"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":20,"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":21,"raw":"[Kanamori et al., 2020] K. Kanamori, T. Takagi, K. Kobayashi, and H. Arimura. DACE: distribution- aware counterfactual explanation by mixed-integer linear optimization. In Proc. of IJCAI'20, pages 2855-2862, 2020.","title":"DACE: distributionaware counterfactual explanation by mixed-integer linear optimization","authors":"K Kanamori, T Takagi, K Kobayashi, H Arimura","year":"2020","venue":"Proc. of IJCAI'20","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Ke et al., 2017] G. Ke, Q. Meng, Th. Finley, T. Wang, W. Chen, W. Ma, Q. Ye, and T. Liu. Lightgbm: A highly efficient gradient boosting decision tree. In Proc. of NeurIPS'17, pages 3146-3154, 2017.","title":"Lightgbm: A highly efficient gradient boosting decision tree","authors":"G Ke, Q Meng, Th, T Finley, W Wang, W Chen, Q Ma, T Ye, Liu","year":"2017","venue":"Proc. of NeurIPS'17","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Koenker, 2005] R. Koenker. Quantile Regression. Econo- metric Society Monographs. Cambridge University Press, 2005.","title":"Quantile Regression","authors":"R Koenker","year":"2005","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Kontokosta, 2019] S. Papadopoulosand C. Kontokosta. Grading buildings on energy performance using city benchmarking data. Applied Energy, 233:244-253, 2019.","title":"Grading buildings on energy performance using city benchmarking data","authors":"S Papadopoulosand, C Kontokosta","year":"2019","venue":"Applied Energy","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Letzgus et al., 2022] S. Letzgus, P. Wagner, J. Lederer, W. Samek, K.R. Müller, and G. Montavon. Toward ex- plainable artificial intelligence for regression models: A methodological perspective. IEEE Signal Process. Mag., 39(4):40-58, 2022.","title":"Toward explainable artificial intelligence for regression models: A methodological perspective","authors":"S Letzgus, P Wagner, J Lederer, W Samek, K R Müller, G Montavon","year":"2022","venue":"IEEE Signal Process. Mag","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Ling and Kenny, 1981] R. Ling and D. Kenny. Correlation and causation. Journal of the American Statistical Associ- ation, 77:489, 1981.","title":"Correlation and causation","authors":"R Ling, D Kenny","year":"1981","venue":"Journal of the American Statistical Association","doi":null,"url":null,"internal_url":null},{"position":27,"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":28,"raw":"[Marques-Silva and Ignatiev, 2022] J. Marques-Silva and A. Ignatiev. Delivering trustworthy AI through formal XAI. In Proc. of AAAI'22, pages 12342-12350, 2022.","title":"Delivering trustworthy AI through formal XAI","authors":"Marques-Silva Ignatiev, ; ] J Marques-Silva, A Ignatiev","year":"2022","venue":"Proc. of AAAI'22","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Miller, 2019] T. Miller. Explanation in artificial intelli- gence: Insights from the social sciences. Artificial Intel- ligence, 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":30,"raw":"[Molnar, 2019] Ch. Molnar. Interpretable Machine Learn- ing -A Guide for Making Black Box Models Explainable. Leanpub, 2019.","title":"Interpretable Machine Learning -A Guide for Making Black Box Models Explainable","authors":"Ch Molnar, Molnar","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Moore and Bell, 2022] A. Moore and M. Bell. XGBoost, a novel explainable AI technique, in the prediction of my- ocardial infarction, a UK biobank cohort study. medRxiv, 2022.","title":"XGBoost, a novel explainable AI technique, in the prediction of myocardial infarction, a UK biobank cohort study","authors":"A Moore, M Bell","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":32,"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 expla- nation. 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":33,"raw":"[Parmentier and Vidal, 2021] A. Parmentier and T. Vidal. Optimal counterfactual explanations in tree ensembles. In Proc. of ICML'21, volume 139 of Proceedings of Machine Learning Research, 2021.","title":"Optimal counterfactual explanations in tree ensembles","authors":"A Parmentier, T Vidal","year":"2021","venue":"Proceedings of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Rudin et al., 2021] C. Rudin, C. Chen, Z. Chen, H. Huang, L. Semenova, and C. Zhong. Interpretable machine learn- ing: Fundamental principles and 10 grand challenges. CoRR, abs/2103.11251, 2021.","title":"Interpretable machine learning: Fundamental principles and 10 grand challenges","authors":"C Rudin, C Chen, Z Chen, H Huang, L Semenova, C Zhong","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":35,"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":36,"raw":"[Strumbelj and Kononenko, 2011] E. Strumbelj and I. Kononenko. A general method for visualizing and explaining black-box regression models. In Adaptive and Natural Computing Algorithms ICANNGA, volume 6594 of LNCS, pages 21-30, 2011.","title":"A general method for visualizing and explaining black-box regression models","authors":"E Strumbelj, I Kononenko","year":"2011","venue":"Adaptive and Natural Computing Algorithms ICANNGA","doi":null,"url":null,"internal_url":null},{"position":37,"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."}