{"type":"ScholarlyArticle","title":"Relation-Based Counterfactual Explanations for Bayesian Network Classifiers","authors":[{"name":"Emanuele Albini","slug":"emanuele-albini","given":"Emanuele","family":"Albini","affiliation":"Dipartimento di Ingegneria dell'Informazione , Università degli Studi di Brescia , Italy; Department of Computing , Imperial College London , UK"},{"name":"Antonio Rago","slug":"antonio-rago","given":"Antonio","family":"Rago","affiliation":"Department of Computing , Imperial College London , UK"},{"name":"Pietro Baroni","slug":"pietro-baroni","given":"Pietro","family":"Baroni","affiliation":"Dipartimento di Ingegneria dell'Informazione , Università degli Studi di Brescia , Italy"},{"name":"Francesca Toni","slug":"francesca-toni","given":"Francesca","family":"Toni","affiliation":"Department of Computing , Imperial College London , UK"}],"abstract":"We propose a general method for generating counterfactual explanations (CFXs) for a range of Bayesian Network Classifiers (BCs), e.g. single- or multi-label, binary or multidimensional. We focus on explanations built from relations of (critical and potential) influence between variables, indicating the reasons for classifications, rather than any probabilistic information. We show by means of a theoretical analysis of CFXs’ properties that they serve the purpose of indicating (potentially) pivotal factors in the classification process, whose absence would give rise to different classifications. We then prove empirically for various BCs that CFXs provide useful information in real world settings, e.g. when race plays a part in parole violation prediction, and show that they have inherent advantages over existing explanation methods in the literature.","doi":"10.24963/ijcai.2020/63","url":"https://ijcai.org/proceedings/2020/63","pdf":"https://ijcai.org/proceedings/2020/0063.pdf","markdown":"https://ijcai.org/proceedings/2020/63.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/63","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":"AI Ethics","track":"Main track","number":63,"pages":{"first":451,"last":457},"keywords":["Uncertainty in AI: Bayesian Networks","AI Ethics: Explainability"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/25644/file_25644.m3u8","length_sec":320,"provider":"hls"}],"references":[{"position":1,"raw":"[Bach et al., 2015] Sebastian Bach, Alexander Binder, Grégoire Montavon, Frederick Klauschen, Klaus-Robert Müller, and Wojciech Samek. On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLOS ONE, 10(7):1-46, 07 2015.","title":"On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation","authors":"Sebastian Bach, Alexander Binder, Grégoire Montavon, Frederick Klauschen, Klaus-Robert Müller, Wojciech Samek","year":"2015","venue":"PLOS ONE","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bau et al., 2017] David Bau, Bolei Zhou, Aditya Khosla, Aude Oliva, and Antonio Torralba. Network dissection: Quantifying interpretability of deep visual representations. In 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21-26, 2017, pages 3319-3327, 2017.","title":"Network dissection: Quantifying interpretability of deep visual representations","authors":"David Bau, Bolei Zhou, Aditya Khosla, Aude Oliva, Antonio Torralba","year":"2017","venue":"2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bielza and Larrañaga, 2014] Concha Bielza and Pedro Larrañaga. Discrete Bayesian network classifiers: A survey. ACM Computing Surveys, 47(1):5:1-5:43, 2014.","title":"Concha Bielza and Pedro Larrañaga. Discrete Bayesian network classifiers: A survey","authors":"Larrañaga Bielza","year":"2014","venue":"ACM Computing Surveys","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chen et al., 2015] Suming Jeremiah Chen, Arthur Choi, and Adnan Darwiche. Value of information based on decision robustness. In Proceedings of the Twenty-Ninth AAAI Con- ference on Artificial Intelligence, January 25-30, 2015, Austin, Texas, USA, pages 3503-3510, 2015.","title":"Value of information based on decision robustness","authors":"Chen","year":"2015","venue":"Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Choi et al., 2012] Arthur Choi, Yexiang Xue, and Adnan Darwiche. Same-decision probability: A confidence mea- sure for threshold-based decisions. International Journal of Approximate Reasoning, 53(9):1415-1428, 2012.","title":"Same-decision probability: A confidence measure for threshold-based decisions","authors":"Arthur Choi, Yexiang Xue, Adnan Darwiche","year":"2012","venue":"International Journal of Approximate Reasoning","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Friedman et al., 1997] Nir Friedman, Dan Geiger, and Moisés Goldszmidt. Bayesian network classifiers. Ma- chine Learning, 29(2-3):131-163, 1997.","title":"Bayesian network classifiers","authors":"Nir Friedman, Dan Geiger, Moisés Goldszmidt","year":"1997","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Guidotti et al., 2019] 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, 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 Computing Surveys","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Koller and Sahami, 1996] Daphne Koller and Mehran Sa- hami. Toward optimal feature selection. In Machine Learning, Proceedings of the Thirteenth International Conference (ICML '96), Bari, Italy, July 3-6, 1996, pages 284-292, 1996.","title":"Toward optimal feature selection","authors":"Sahami Koller","year":"1996","venue":"Proceedings of the Thirteenth International Conference (ICML '96)","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Lacave and Díez, 2002] Carmen Lacave and Fran- cisco Javier Díez. A review of explanation methods for Bayesian networks. Knowledge Engineering Review, 17(2):107-127, 2002.","title":"Carmen Lacave and Francisco Javier Díez. A review of explanation methods for Bayesian networks","authors":"Díez Lacave","year":"2002","venue":"Knowledge Engineering Review","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Lacave et al., 2000] Carmen Lacave, Roberto Atienza, and Francisco Javier Díez. Graphical explanation in Bayesian networks. In Medical Data Analysis, First International Symposium, ISMDA 2000, Frankfurt, Germany, September 29-30, 2000, Proceedings, pages 122-129, 2000.","title":"Graphical explanation in Bayesian networks","authors":"Carmen Lacave, Roberto Atienza, Francisco Javier, Díez","year":"2000","venue":"Medical Data Analysis, First International Symposium, ISMDA 2000","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Lombrozo, 2007] Tania Lombrozo. Simplicity and prob- ability in causal explanation. Cognitive Psychology, 55:232-257, 2007.","title":"Simplicity and probability in causal explanation","authors":"Tania Lombrozo","year":"2007","venue":"Cognitive Psychology","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Lundberg and Lee, 2017] Scott M. Lundberg and Su-In Lee. A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Sys- tems 2017, 4-9 December 2017, Long Beach, CA, USA, pages 4765-4774, 2017.","title":"A unified approach to interpreting model predictions","authors":"M Scott, Su-In Lundberg, Lee","year":"2017","venue":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Maron and Kuhns, 1960] M. E. Maron and J. L. Kuhns. On relevance, probabilistic indexing and information retrieval. Journal of the ACM, 7(3):216-244, 1960.","title":"On relevance, probabilistic indexing and information retrieval","authors":"M E Maron, J L Kuhns","year":"1960","venue":"Journal of the ACM","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Miller, 2019] Tim 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":"Tim Miller, Miller","year":"2019","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Nielsen et al., 2008] Ulf H. Nielsen, Jean-Philippe Pellet, and André Elisseeff. Explanation trees for causal Bayesian networks. In UAI 2008, Proceedings of the 24th Con- ference in Uncertainty in Artificial Intelligence, Helsinki, Finland, July 9-12, 2008, pages 427-434, 2008.","title":"Explanation trees for causal Bayesian networks","authors":"H Ulf, Jean-Philippe Nielsen, André Pellet, Elisseeff","year":"2008","venue":"Proceedings of the 24th Conference in Uncertainty in Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Pearl, 1989] Judea Pearl. Probabilistic reasoning in intel- ligent systems -networks of plausible inference. Morgan Kaufmann series in representation and reasoning. Morgan Kaufmann, 1989.","title":"Judea Pearl. Probabilistic reasoning in intelligent systems -networks of plausible inference","authors":"Pearl","year":"1989","venue":"Morgan Kaufmann series in representation and reasoning","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Ribeiro et al., 2016] Marco Túlio Ribeiro, Sameer Singh, and Carlos Guestrin. \"Why should I trust you?\": Ex- plaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, August 13-17, 2016, 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":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Ribeiro et al., 2018] Marco Túlio Ribeiro, Sameer Singh, and Carlos Guestrin. Anchors: High-precision model- agnostic explanations. In Proceedings of the Thirty- Second AAAI Conference on Artificial Intelligence, AAAI- 18, New Orleans, Louisiana, USA, February 2-7, 2018, pages 1527-1535, 2018.","title":"Anchors: High-precision modelagnostic explanations","authors":"Marco Túlio Ribeiro, Sameer Singh, Carlos Guestrin","year":"2018","venue":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, AAAI-18","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Schwab and Karlen, 2019] Patrick Schwab and Walter Karlen. CXPlain: Causal explanations for model in- terpretation under uncertainty. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, 8-14 December 2019, Vancouver, BC, Canada, pages 10220-10230, 2019.","title":"CXPlain: Causal explanations for model interpretation under uncertainty","authors":"Karlen ; Schwab, Patrick Schwab, Walter Karlen","year":"2019","venue":"Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Shih et al., 2018] Andy Shih, Arthur Choi, and Adnan Dar- wiche. A symbolic approach to explaining Bayesian net- work classifiers. In Proceedings of the Twenty-Seventh In- ternational Joint Conference on Artificial Intelligence, IJ- CAI 2018, July 13-19, 2018, Stockholm, Sweden, pages 5103-5111, 2018.","title":"A symbolic approach to explaining Bayesian network classifiers","authors":"Andy Shih, Arthur Choi, Adnan Darwiche","year":"2018","venue":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJ-CAI 2018","doi":null,"url":null,"internal_url":"/proceedings/2018/708"},{"position":21,"raw":"[Shih et al., 2019] Andy Shih, Arthur Choi, and Adnan Dar- wiche. Compiling Bayesian network classifiers into deci- sion graphs. In The Thirty-Third AAAI Conference on Ar- tificial Intelligence, AAAI 2019, Honolulu, Hawaii, USA, January 27 -February 1, 2019, pages 7966-7974, 2019.","title":"Compiling Bayesian network classifiers into decision graphs","authors":"Andy Shih, Arthur Choi, Adnan Darwiche","year":"2019","venue":"The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI 2019","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Simari and Rahwan, 2009] Guillermo Ricardo Simari and Iyad Rahwan, editors. Argumentation in Artificial Intel- ligence. Springer, 2009.","title":"Argumentation in Artificial Intelligence","authors":null,"year":"2009","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Timmer et al., 2015] Sjoerd T. Timmer, John-Jules Ch. Meyer, Henry Prakken, Silja Renooij, and Bart Ver- heij. Explaining Bayesian networks using argumentation. In Symbolic and Quantitative Approaches to Reasoning with Uncertainty -13th European Conference, ECSQARU 2015, Compiègne, France, July 15-17, 2015. Proceedings, pages 83-92, 2015.","title":"Explaining Bayesian networks using argumentation","authors":"T Sjoerd, John-Jules Timmer, Ch, Henry Meyer, Silja Prakken, Bart Renooij, Verheij","year":"2015","venue":"Symbolic and Quantitative Approaches to Reasoning with Uncertainty -13th European Conference, ECSQARU 2015","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}