{"type":"ScholarlyArticle","title":"Optimal Feature Selection for Decision Robustness in Bayesian Networks","authors":[{"name":"YooJung Choi","slug":"yoojung-choi","given":"YooJung","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"},{"name":"Guy Van den Broeck","slug":"guy-van-den-broeck","given":"Guy","family":"Van den Broeck","affiliation":"Computer Science Department University of California , Los Angeles"}],"abstract":"In many applications, one can define a large set of features to support the classification task at hand. At test time, however, these become prohibitively expensive to evaluate, and only a small subset of features is used, often selected for their information-theoretic value. For threshold-based, Naive Bayes classifiers, recent work has suggested selecting features that maximize the expected robustness of the classifier, that is, the expected probability it maintains its decision after seeing more features. We propose the first algorithm to compute this expected same-decision probability for general Bayesian network classifiers, based on compiling the network into a tractable circuit representation. Moreover, we develop a search algorithm for optimal feature selection that utilizes efficient incremental circuit modifications. Experiments on Naive Bayes, as well as more general networks, show the efficacy and distinct behavior of this decision-making approach.","doi":"10.24963/ijcai.2017/215","url":"https://ijcai.org/proceedings/2017/215","pdf":"https://ijcai.org/proceedings/2017/0215.pdf","markdown":"https://ijcai.org/proceedings/2017/215.md","bibtex":"https://ijcai.org/proceedings/2017/bibtex/215","volume":{"slug":"2017","title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2017","url":"https://ijcai.org/proceedings/2017/","year":2017,"location":"Melbourne, Australia","dates":"19-25 August 2017","editors":"Carles Sierra","isbn":"978-0-9992411-0-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2017"},"section":"Machine Learning A-R","track":"Main track","number":215,"pages":{"first":1554,"last":1560},"keywords":["Knowledge Representation, Reasoning, and Logic: Tractable languages and knowledge compilation","Uncertainty in AI: Bayesian Networks","Uncertainty in AI: Decision/Utility Theory","Machine Learning: Feature Selection/Construction"],"videos":[],"references":[{"position":1,"raw":"[Bache and Lichman, 2013] K. Bache and M. Lichman. UCI ma- chine 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":"[Bellala et al., 2013] Gowtham Bellala, Jason Stanley, Suresh K. Bhavnani, and Clayton Scott. A rank-based approach to active diagnosis. IEEE Trans. Pattern Anal. Mach. Intell., 35(9):2078- 2090, 2013.","title":"A rank-based approach to active diagnosis","authors":"Gowtham Bellala, Jason Stanley, K Suresh, Clayton Bhavnani, Scott","year":"2013","venue":"IEEE Trans. Pattern Anal. Mach. Intell","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bilgic and Getoor, 2011] Mustafa Bilgic and Lise Getoor. Value of information lattice: Exploiting probabilistic independence for effective feature subset acquisition. Journal of Artificial Intelli- gence Research (JAIR), 41:69-95, 2011.","title":"Value of information lattice: Exploiting probabilistic independence for effective feature subset acquisition","authors":"Mustafa Bilgic, Lise Getoor","year":"2011","venue":"Journal of Artificial Intelligence Research (JAIR)","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bova, 2016] Simone Bova. SDDs are exponentially more succinct than OBDDs. In Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, pages 929-935. AAAI Press, 2016.","title":"SDDs are exponentially more succinct than OBDDs","authors":"Simone Bova","year":"2016","venue":"Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chavira and Darwiche, 2005] M. Chavira and A. Darwiche. Com- piling bayesian networks with local structure. In Proceedings of IJCAI, volume 5, pages 1306-1312, 2005.","title":"Compiling bayesian networks with local structure","authors":"M Chavira, A Darwiche","year":"2005","venue":"Proceedings of IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2005/111"},{"position":6,"raw":"[Chavira and Darwiche, 2008] M. Chavira and A. Darwiche. On probabilistic inference by weighted model counting. AIJ, 172(6- 7):772-799, 2008.","title":"On probabilistic inference by weighted model counting","authors":"M Chavira, A Darwiche","year":"2008","venue":"AIJ","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Chen et al., 2013] Suming Chen, Arthur Choi, and Adnan Dar- wiche. An exact algorithm for computing the Same-Decision Probability. In Proceedings of the 23rd International Joint Con- ference on Artificial Intelligence, pages 2525-2531, 2013.","title":"An exact algorithm for computing the Same-Decision Probability","authors":"Chen","year":"2013","venue":"Proceedings of the 23rd International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2013/372"},{"position":8,"raw":"[Chen et al., 2014] Suming Chen, Arthur Choi, and Adnan Dar- wiche. Algorithms and applications for the Same-Decision Probability. Journal of Artificial Intelligence Research (JAIR), 49:601-633, 2014.","title":"Algorithms and applications for the Same-Decision Probability","authors":"Chen","year":"2014","venue":"Journal of Artificial Intelligence Research (JAIR)","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Chen et al., 2015a] Suming Chen, Arthur Choi, and Adnan Dar- wiche. Computer adaptive testing using the same-decision proba- bility. In Proceedings of the Twelfth UAI Conference on Bayesian Modeling Applications Workshop, pages 34-43, 2015.","title":"Computer adaptive testing using the same-decision probability","authors":"Chen","year":"2015","venue":"Proceedings of the Twelfth UAI Conference on Bayesian Modeling Applications Workshop","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Chen et al., 2015b] Suming Chen, Arthur Choi, and Adnan Dar- wiche. Value of information based on Decision Robustness. In Proceedings of the 29th Conference on Artificial Intelligence (AAAI), 2015.","title":"Value of information based on Decision Robustness","authors":"Chen","year":"2015","venue":"Proceedings of the 29th Conference on Artificial Intelligence (AAAI)","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Choi et al., 2012] Arthur Choi, Yexiang Xue, and Adnan Dar- wiche. Same-Decision Probability: A confidence measure for threshold-based decisions. International Journal of Approximate Reasoning (IJAR), 2:1415-1428, 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":12,"raw":"[Choi et al., 2013] A. Choi, D. Kisa, and A. Darwiche. Compil- ing probabilistic graphical models using sentential decision dia- grams. In ECSQARU, pages 121-132, 2013.","title":"Compiling probabilistic graphical models using sentential decision diagrams","authors":"A Choi, D Kisa, A Darwiche","year":"2013","venue":"ECSQARU","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Darwiche and Marquis, 2002] A. Darwiche and P. Marquis. A knowledge compilation map. JAIR, 17:229-264, 2002.","title":"A knowledge compilation map","authors":"A Darwiche, P Marquis","year":"2002","venue":"JAIR","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Darwiche et al., 2008] Adnan Darwiche, Rina Dechter, Arthur Choi, Vibhav Gogate, and Lars Otten. Results from the proba- blistic inference evaluation of UAI-08. http://graphmod. ics.uci.edu/uai08/Evaluation/Report, 2008.","title":"Results from the probablistic inference evaluation of UAI-08","authors":"Adnan Darwiche, Rina Dechter, Arthur Choi, Vibhav Gogate, Lars Otten","year":"2008","venue":null,"doi":null,"url":"http://graphmod.ics.uci.edu/uai08/Evaluation/Report","internal_url":null},{"position":15,"raw":"[Darwiche, 2009] Adnan Darwiche. Modeling and Reasoning with Bayesian Networks. Cambridge University Press, 2009.","title":"Modeling and Reasoning with Bayesian Networks","authors":"Adnan Darwiche","year":"2009","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Darwiche, 2011] A. Darwiche. SDD: A new canonical representa- tion of propositional knowledge bases. In Proceedings of IJCAI, pages 819-826, 2011.","title":"SDD: A new canonical representation of propositional knowledge bases","authors":"A Darwiche","year":"2011","venue":"Proceedings of IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2011/143"},{"position":17,"raw":"[Dechter and Mateescu, 2007] Rina Dechter and Robert Mateescu. And/or search spaces for graphical models. Artificial intelligence, 171(2-3):73-106, 2007.","title":"And/or search spaces for graphical models","authors":"Rina Dechter, Robert Mateescu","year":"2007","venue":"Artificial intelligence","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Fierens et al., 2015] Daan Fierens, Guy Van den Broeck, Joris Renkens, Dimitar Shterionov, Bernd Gutmann, Ingo Thon, Gerda Janssens, and Luc De Raedt. Inference and learning in probabilis- tic logic programs using weighted Boolean formulas. Theory and Practice of Logic Programming, 15:358-401, 5 2015.","title":"Inference and learning in probabilistic logic programs using weighted Boolean formulas","authors":"Daan Fierens, Guy Van Den, Joris Broeck, Dimitar Renkens, Bernd Shterionov, Ingo Gutmann, Gerda Thon, Luc Janssens, Raedt De","year":"2015","venue":"Theory and Practice of Logic Programming","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Gao and Koller, 2011] T. Gao and D. Koller. Active classification based on value of classifier. In Advances in Neural Information Processing Systems (NIPS 2011), 2011.","title":"Active classification based on value of classifier","authors":"T Gao, D Koller","year":"2011","venue":"Advances in Neural Information Processing Systems (NIPS 2011)","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Gimenez et al., 2014] Francisco J Gimenez, Yirong Wu, Eliza- beth S Burnside, and Daniel L Rubin. A novel method to assess incompleteness of mammography reports. In AMIA Annual Sym- posium Proceedings, volume 2014, page 1758. American Medi- cal Informatics Association, 2014.","title":"A novel method to assess incompleteness of mammography reports","authors":"Gimenez","year":"2014","venue":"AMIA Annual Symposium Proceedings","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Heckerman et al., 1993] David Heckerman, Eric Horvitz, and Blackford Middleton. An approximate nonmyopic computation for value of information. IEEE Transactions on Pattern Analysis and Machine Intelligence, 15(3):292-298, 1993.","title":"An approximate nonmyopic computation for value of information","authors":"David Heckerman, Eric Horvitz, Blackford Middleton","year":"1993","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Huang et al., 2006] Jinbo Huang, Mark Chavira, Adnan Darwiche, et al. Solving map exactly by searching on compiled arithmetic circuits. In AAAI, volume 6, pages 3-7, 2006.","title":"Solving map exactly by searching on compiled arithmetic circuits","authors":"Jinbo Huang, Mark Chavira, Adnan Darwiche","year":"2006","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Korf, 2009] Richard E Korf. Multi-way number partitioning. In IJCAI, pages 538-543. Citeseer, 2009.","title":"Multi-way number partitioning","authors":"Richard E Korf","year":"2009","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2009/96"},{"position":24,"raw":"[Krause and Guestrin, 2009] Andreas Krause and Carlos Guestrin. Optimal value of information in graphical models. Journal of Artificial Intelligence Research (JAIR), 35:557-591, 2009.","title":"Optimal value of information in graphical models","authors":"Guestrin Krause, Andreas Krause, Carlos Guestrin","year":"2009","venue":"Journal of Artificial Intelligence Research (JAIR)","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Malings and Pozzi, 2016] Carl Malings and Matteo Pozzi. Condi- tional entropy and value of information metrics for optimal sens- ing in infrastructure systems. Structural Safety, 60:77-90, 2016.","title":"Conditional entropy and value of information metrics for optimal sensing in infrastructure systems","authors":"Pozzi Malings, Carl Malings, Matteo Pozzi","year":"2016","venue":"Structural Safety","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Millán and Pérez-De-La-Cruz, 2002] Eva Millán and José Luis Pérez-De-La-Cruz. A Bayesian diagnostic algorithm for student modeling and its evaluation. User Modeling and User-Adapted Interaction, 12(2-3):281-330, 2002.","title":"Eva Millán and José Luis Pérez-De-La-Cruz. A Bayesian diagnostic algorithm for student modeling and its evaluation","authors":"Pérez-De-La-Cruz Millán","year":"2002","venue":"User Modeling and User-Adapted Interaction","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Munie and Shoham, 2008] Michael Munie and Yoav Shoham. Op- timal testing of structured knowledge. In Proceedings of the 23rd National Conference on Artificial intelligence, pages 1069-1074, 2008.","title":"Optimal testing of structured knowledge","authors":"Shoham Munie, Michael Munie, Yoav Shoham","year":"2008","venue":"Proceedings of the 23rd National Conference on Artificial intelligence","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Oztok et al., 2016] Umut Oztok, Arthur Choi, and Adnan Dar- wiche. Solving PP PP -complete problems using knowledge com- pilation. In Proceedings of the 15th International Conference on Principles of Knowledge Representation and Reasoning (KR), pages 94-103, 2016.","title":"Solving PP PP -complete problems using knowledge compilation","authors":"Umut Oztok, Arthur Choi, Adnan Darwiche","year":"2016","venue":"Proceedings of the 15th International Conference on Principles of Knowledge Representation and Reasoning (KR)","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Sang et al., 2005] Tian Sang, Paul Beame, and Henry A Kautz. Performing bayesian inference by weighted model counting. In AAAI, volume 5, pages 475-481, 2005.","title":"Performing bayesian inference by weighted model counting","authors":"Tian Sang, Paul Beame, Henry A Kautz","year":"2005","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Selman and Kautz, 1996] Bart Selman and Henry Kautz. Knowl- edge compilation and theory approximation. Journal of the ACM (JACM), 43(2):193-224, 1996.","title":"Knowledge compilation and theory approximation","authors":"Kautz Selman, Bart Selman, Henry Kautz","year":"1996","venue":"Journal of the ACM (JACM)","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Van den Broeck and Darwiche, 2015] G. Van den Broeck and A. Darwiche. On the role of canonicity in knowledge compi- lation. In Proceedings of the 29th Conference on Artificial Intel- ligence (AAAI), 2015.","title":"On the role of canonicity in knowledge compilation","authors":"Broeck Van Den, ] G Darwiche, A Van Den Broeck, Darwiche","year":"2015","venue":"Proceedings of the 29th Conference on Artificial Intelligence (AAAI)","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Yu et al., 2009] Shipeng Yu, Balaji Krishnapuram, Romer Ros- ales, and R Bharat Rao. Active sensing. In International Con- ference on Artificial Intelligence and Statistics, pages 639-646, 2009.","title":"Active sensing","authors":"Shipeng Yu, Balaji Krishnapuram, Romer Rosales, Bharat Rao","year":"2009","venue":"International Conference on Artificial Intelligence and Statistics","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Zhang and Ji, 2010] Yongmian Zhang and Qiang Ji. Efficient sen- sor selection for active information fusion. IEEE Transactions on Systems, Man, and Cybernetics, Part B, 40(3):719-728, June 2010.","title":"Efficient sensor selection for active information fusion","authors":"Ji ; Zhang, Yongmian Zhang, Qiang Ji","year":"2010","venue":"IEEE Transactions on Systems, Man, and Cybernetics, Part B","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}