{"type":"ScholarlyArticle","title":"A Symbolic Approach to Explaining Bayesian Network Classifiers","authors":[{"name":"Andy Shih","slug":"andy-shih","given":"Andy","family":"Shih","affiliation":"Computer Science Department , University of California , Los Angeles"},{"name":"Arthur Choi","slug":"arthur-choi","given":"Arthur","family":"Choi","affiliation":"Computer Science Department , University of California , Los Angeles"},{"name":"Adnan Darwiche","slug":"adnan-darwiche","given":"Adnan","family":"Darwiche","affiliation":"Computer Science Department , University of California , Los Angeles"}],"abstract":"We propose an approach for explaining Bayesian network classifiers, which is based on compiling such classifiers into decision functions that have a tractable and symbolic form. We introduce two types of explanations for why a classifier may have classified an instance positively or negatively and suggest algorithms for computing these explanations. The first type of explanation identifies a minimal set of the currently active features that is responsible for the current classification, while the second type of explanation identifies a minimal set of features whose current state (active or not) is sufficient for the classification. We consider in particular the compilation of Naive and Latent-Tree Bayesian network classifiers into Ordered Decision Diagrams (ODDs), providing a context for evaluating our proposal using case studies and experiments based on classifiers from the literature.","doi":"10.24963/ijcai.2018/708","url":"https://ijcai.org/proceedings/2018/708","pdf":"https://ijcai.org/proceedings/2018/0708.pdf","markdown":"https://ijcai.org/proceedings/2018/708.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/708","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Uncertainty in AI","track":"Main track","number":708,"pages":{"first":5103,"last":5111},"keywords":["Knowledge Representation and Reasoning: Tractable Languages and Knowledge compilation","Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning","Uncertainty in AI: Bayesian Networks","Machine Learning: Interpretability"],"videos":[],"references":[{"position":1,"raw":"[Bache and Lichman, 2013] K. Bache and M. Lichman. UCI machine learning repository, 2013.","title":"UCI machine learning repository","authors":"K Bache, M Lichman","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bryant, 1986] R. E. Bryant. Graph-based algorithms for Boolean function manipulation. IEEE Transactions on Computers, C-35:677-691, 1986.","title":"Graph-based algorithms for Boolean function manipulation","authors":"R E Bryant","year":"1986","venue":"IEEE Transactions on Computers","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chan and Darwiche, 2003] Hei Chan and Adnan Darwiche. Reasoning about Bayesian network classifiers. In Proceed- ings of the Nineteenth Conference on Uncertainty in Arti- ficial Intelligence (UAI), pages 107-115, 2003.","title":"Reasoning about Bayesian network classifiers","authors":"Chan, Darwiche ; ] Hei Chan, Adnan Darwiche","year":"2003","venue":"Proceedings of the Nineteenth Conference on Uncertainty in Artificial Intelligence (UAI)","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Chen et al., 2014] Suming Chen, Arthur Choi, and Adnan Darwiche. Algorithms and applications for the same- decision probability. Journal of Artificial Intelligence Re- search (JAIR), 49:601-633, 2014.","title":"Algorithms and applications for the samedecision probability","authors":"Chen","year":"2014","venue":"Journal of Artificial Intelligence Research (JAIR)","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 Jour- nal of Approximate Reasoning (IJAR), 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 (IJAR)","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Choi et al., 2013] Arthur Choi, Doga Kisa, and Adnan Dar- wiche. Compiling probabilistic graphical models us- ing sentential decision diagrams. In Proceedings of the 12th European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty (ECSQARU), pages 121-132, 2013.","title":"Compiling probabilistic graphical models using sentential decision diagrams","authors":"Choi","year":"2013","venue":"Proceedings of the 12th European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty (ECSQARU)","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Choi et al., 2017] YooJung Choi, Adnan Darwiche, and Guy Van den Broeck. Optimal feature selection for de- cision robustness in Bayesian networks. In Proceedings of the 26th International Joint Conference on Artificial Intel- ligence (IJCAI), pages 1554-1560, August 2017.","title":"Optimal feature selection for decision robustness in Bayesian networks","authors":"Choi","year":"2017","venue":"Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI)","doi":null,"url":null,"internal_url":"/proceedings/2017/215"},{"position":8,"raw":"[Coudert and Madre, 1993] Olivier Coudert and Jean Christophe Madre. Fault tree analysis: 10 20 prime implicants and beyond. In Proc. of the Annual Re- liability and Maintainability Symposium, pages 240-245, 1993.","title":"Fault tree analysis: 10 20 prime implicants and beyond","authors":"Madre Coudert, Olivier Coudert, Jean Christophe, Madre","year":"1993","venue":"Proc. of the Annual Reliability and Maintainability Symposium","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Coudert et al., 1993] Olivier Coudert, Jean Christophe Madre, Henri Fraisse, and Herve Touati. Implicit prime cover computation: An overview. In Proceedings of the 4th SASIMI Workshop, 1993.","title":"Implicit prime cover computation: An overview","authors":"Olivier Coudert, Jean Christophe Madre, Henri Fraisse, Herve Touati","year":"1993","venue":"Proceedings of the 4th SASIMI Workshop","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Darwiche and Choi, 2010] Adnan Darwiche and Arthur Choi. Same-decision probability: A confidence measure for threshold-based decisions under noisy sensors. In Pro- ceedings of the Fifth European Workshop on Probabilistic Graphical Models (PGM), pages 113-120, 2010.","title":"Same-decision probability: A confidence measure for threshold-based decisions under noisy sensors","authors":"Choi Darwiche, Adnan Darwiche, Arthur Choi","year":"2010","venue":"Proceedings of the Fifth European Workshop on Probabilistic Graphical Models (PGM)","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Darwiche and Marquis, 2002] Adnan Darwiche and Pierre Marquis. A knowledge compilation map. Journal of Arti- ficial Intelligence Research (JAIR), 17:229-264, 2002.","title":"A knowledge compilation map","authors":"Adnan Darwiche, Pierre Marquis","year":"2002","venue":"Journal of Artificial Intelligence Research (JAIR)","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Darwiche, 2001] Adnan Darwiche. Decomposable negation normal form. Journal of the ACM, 48(4):608-647, 2001.","title":"Decomposable negation normal form","authors":"Adnan Darwiche","year":"2001","venue":"Journal of the ACM","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Elenberg et al., 2017] Ethan R. Elenberg, Alexandros G. Dimakis, Moran Feldman, and Amin Karbasi. Streaming weak submodularity: Interpreting neural networks on the fly. In Advances in Neural Information Processing Systems 30 (NIPS), pages 4047-4057, 2017.","title":"Streaming weak submodularity: Interpreting neural networks on the fly","authors":"Ethan R Elenberg, Alexandros G Dimakis, Moran Feldman, Amin Karbasi","year":"2017","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"Takashi Horiyama and Toshi- hide Ibaraki. Ordered binary decision diagrams as knowledge-bases. Artificial Intelligence (AIJ), 136(2):189-213, 2002.","title":"Ordered binary decision diagrams as knowledge-bases","authors":"Takashi Horiyama, Toshihide Ibaraki","year":"2002","venue":"Artificial Intelligence (AIJ)","doi":null,"url":null,"internal_url":null},{"position":15,"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 (NIPS), pages 4768-4777, 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","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Meinel and Theobald, 1998] Christoph Meinel and Thorsten Theobald. Algorithms and Data Structures in VLSI Design: OBDD -Foundations and Applications. Springer, 1998.","title":"Algorithms and Data Structures in VLSI Design: OBDD -Foundations and Applications","authors":"Theobald ; Meinel, Christoph Meinel, Thorsten Theobald","year":"1998","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Minato, 1993] Shin-ichi Minato. Fast generation of prime- irredundant covers from binary decision diagrams. IEICE Transactions on Fundamentals of Electronics, Communi- cations and Computer Sciences, 76(6):967-973, 1993.","title":"Fast generation of primeirredundant covers from binary decision diagrams","authors":"Shin-Ichi Minato","year":"1993","venue":"IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Ribeiro et al., 2016a] Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. Nothing else matters: Model- agnostic explanations by identifying prediction invariance. In NIPS Workshop on Interpretable Machine Learning in Complex Systems, 2016.","title":"Nothing else matters: Modelagnostic explanations by identifying prediction invariance","authors":"Ribeiro","year":"2016","venue":"NIPS Workshop on Interpretable Machine Learning in Complex Systems","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Ribeiro et al., 2016b] Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. \"Why should I trust you?\": Explain- ing the predictions of any classifier. In Knowledge Discov- ery and Data Mining (KDD), pages 1135-1144, 2016.","title":"Why should I trust you?\": Explaining the predictions of any classifier","authors":"Ribeiro","year":"2016","venue":"Knowledge Discovery and Data Mining (KDD)","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Ribeiro et al., 2018] Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. Anchors: High-precision model- agnostic explanations. In Proceedings of the Thirty- Second AAAI Conference on Artificial Intelligence (AAAI), pages 1527-1535, 2018.","title":"Anchors: High-precision modelagnostic explanations","authors":"Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin","year":"2018","venue":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI)","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[van der Gaag et al., 2004] Linda C. van der Gaag, Hans L. Bodlaender, and A. J. Feelders. Monotonicity in Bayesian networks. In Proceedings of the 20th Conference in Un- certainty in Artificial Intelligence (UAI), pages 569-576, 2004.","title":"Monotonicity in Bayesian networks","authors":"Linda C Van Der Gaag, Hans L Bodlaender, A J Feelders","year":"2004","venue":"Proceedings of the 20th Conference in Uncertainty in Artificial Intelligence (UAI)","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Wegener, 2000] Ingo Wegener. Branching Programs and Binary Decision Diagrams. SIAM, 2000.","title":"Branching Programs and Binary Decision Diagrams","authors":"Ingo Wegener","year":"2000","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}