{"type":"ScholarlyArticle","title":"Neural Representation and Learning of Hierarchical 2-additive Choquet Integrals","authors":[{"name":"Roman Bresson","slug":"roman-bresson","given":"Roman","family":"Bresson","affiliation":"Thales Research and Technology , 91767 Palaiseau , France; LRI , CNRS -INRIA , Université Paris-Saclay , 91400 Orsay , France"},{"name":"Johanne Cohen","slug":"johanne-cohen","given":"Johanne","family":"Cohen","affiliation":"LRI , CNRS -INRIA , Université Paris-Saclay , 91400 Orsay , France"},{"name":"Eyke Hüllermeier","slug":"eyke-hullermeier","given":"Eyke","family":"Hüllermeier","affiliation":"Department of Computer Science , Paderborn University , 33098 Paderborn , Germany"},{"name":"Christophe Labreuche","slug":"christophe-labreuche","given":"Christophe","family":"Labreuche","affiliation":"Thales Research and Technology , 91767 Palaiseau , France"},{"name":"Michèle Sebag","slug":"michele-sebag","given":"Michèle","family":"Sebag","affiliation":"LRI , CNRS -INRIA , Université Paris-Saclay , 91400 Orsay , France"}],"abstract":"Multi-Criteria Decision Making (MCDM) aims at modelling expert preferences and assisting decision makers in identifying options best accommodating expert criteria. An instance of MCDM model, the Choquet integral is widely used in real-world applications, due to its ability to capture interactions between criteria while retaining interpretability. Aimed at a better scalability and modularity, hierarchical Choquet integrals involve intermediate aggregations of the interacting criteria, at the cost of a more complex elicitation. The paper presents a machine learning-based approach for the automatic identification of hierarchical MCDM models, composed of 2-additive Choquet integral aggregators and of marginal utility functions on the raw features from data reflecting expert preferences. The proposed NEUR-HCI framework relies on a specific neural architecture, enforcing by design the Choquet model constraints and supporting its end-to-end training. The empirical validation of NEUR-HCI on real-world and artificial benchmarks demonstrates the merits of the approach compared to state-of-art baselines.","doi":"10.24963/ijcai.2020/275","url":"https://ijcai.org/proceedings/2020/275","pdf":"https://ijcai.org/proceedings/2020/0275.pdf","markdown":"https://ijcai.org/proceedings/2020/275.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/275","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":"Machine Learning","track":"Main track","number":275,"pages":{"first":1984,"last":1991},"keywords":["Knowledge Representation and Reasoning: Utility Theory","Knowledge Representation and Reasoning: Preference Modelling and Preference-Based Reasoning","Machine Learning: Knowledge-based Learning","Machine Learning: Learning Preferences or Rankings"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/24391/file_24391.m3u8","length_sec":303,"provider":"hls"}],"references":[{"position":1,"raw":"[Alavi et al., 2009] Sajid H. Alavi, Javad Jassbi, Paulo J. A. Serra, and Rita A. Ribeiro. Defining Fuzzy Measures: A Comparative Study with Genetic and Gradient Descent Al- gorithms. In J. A. Tenreiro Machado, Béla Pátkai, and Imre J. Rudas, editors, Intelligent Engineering Systems and Computational Cybernetics, pages 427-437. Springer, 2009.","title":"Defining Fuzzy Measures: A Comparative Study with Genetic and Gradient Descent Algorithms","authors":"H Sajid, Javad Alavi, Paulo J A Jassbi, Rita A Serra, Ribeiro","year":"2009","venue":"Intelligent Engineering Systems and Computational Cybernetics","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Benabbou et al., 2017] Nawal Benabbou, Patrice Perny, and Paolo Viappiani. Incremental elicitation of Choquet ca- pacities for multicriteria choice, ranking and sorting prob- lems. Artificial Intelligence, 246:152-180, 2017.","title":"Incremental elicitation of Choquet capacities for multicriteria choice, ranking and sorting problems","authors":"Nawal Benabbou, Patrice Perny, Paolo Viappiani","year":"2017","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bourdache et al., 2019] Nadjet Bourdache, Patrice Perny, and Olivier Spanjaard. Incremental Elicitation of Rank- Dependent Aggregation Functions based on Bayesian Lin- ear Regression. In IJCAI-19, pages 2023-2029, 2019.","title":"Incremental Elicitation of Rank-Dependent Aggregation Functions based on Bayesian Linear Regression","authors":"Bourdache","year":"2019","venue":"IJCAI-19","doi":null,"url":null,"internal_url":"/proceedings/2019/280"},{"position":4,"raw":"[Bous and Pirlot, 2013] Géraldine Bous and Marc Pirlot. Learning Multicriteria Utility Functions with Random Utility Models. In ADT-13, pages 101-115. 2013.","title":"Learning Multicriteria Utility Functions with Random Utility Models","authors":"Pirlot Bous","year":"2013","venue":"ADT-13","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Bromley et al., 1993] Jane Bromley, Isabelle Guyon, Yann Lecun, Eduard Säckinger, and Roopak Shah. Signature verification using a siamese time delay neural network. Int. J. of Pattern Recognition and AI, 7:737-744, 1993.","title":"Signature verification using a siamese time delay neural network","authors":"Jane Bromley, Isabelle Guyon, Yann Lecun, Eduard Säckinger, Roopak Shah","year":"1993","venue":"Int. J. of Pattern Recognition and AI","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Burges et al., 2006] Christopher J. C. Burges, Robert Ragno, and Quoc Viet Le. Learning to rank with non- smooth cost functions. In Bernhard Schölkopf, John C. Platt, and Thomas Hofmann, editors, Neural Informa- tion Processing Systems NIPS, pages 193-200. MIT Press, 2006.","title":"Learning to rank with nonsmooth cost functions","authors":"J C Christopher, Robert Burges, Quoc Ragno, Le Viet","year":"2006","venue":"Neural Information Processing Systems NIPS","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Cybenko, 1989] G. Cybenko. Approximations by superpo- sitions of sigmoidal functions. Mathematics of Control, Signals, and Systems, 2(4):303-314, 1989.","title":"Approximations by superpositions of sigmoidal functions","authors":"G Cybenko","year":"1989","venue":"Mathematics of Control, Signals, and Systems","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Fallah Tehrani et al., 2014] Ali Fallah Tehrani, Christophe Labreuche, and Eyke Hüllermeier. Choquistic Utilitaris- tic Regression. In DA2PL-14, 2014.","title":"Choquistic Utilitaristic Regression","authors":"Fallah Tehrani","year":"2014","venue":"DA2PL-14","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Fallah Tehrani et al., 2012] Ali Fallah Tehrani, Weiwei Cheng, Krzysztof Dembczyński, and Eyke Hüllermeier. Learning monotone nonlinear models using the Choquet integral. Machine Learning, 89(1):183-211, 2012.","title":"Learning monotone nonlinear models using the Choquet integral","authors":"Fallah Tehrani","year":"2012","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Fishburn, 1970] Peter C Fishburn. Utility theory for deci- sion making. Wiley, 1970.","title":"Utility theory for decision making","authors":"Peter C Fishburn","year":"1970","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Fürnkranz and Hüllermeier, 2011] Johannes Fürnkranz and Eyke Hüllermeier. Preference Learning and Ranking by Pairwise Comparison. In Johannes Fürnkranz and Eyke Hüllermeier, editors, Preference Learning, pages 65-82. Springer, 2011.","title":"Preference Learning and Ranking by Pairwise Comparison","authors":"Hüllermeier Fürnkranz, Johannes Fürnkranz, Eyke Hüllermeier","year":"2011","venue":"Preference Learning","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Grabisch and Labreuche, 2010] Michel Grabisch and Christophe Labreuche. A decade of application of the Choquet and Sugeno integrals in multi-criteria decision aid. ANOR, 175:247-286, 2010.","title":"A decade of application of the Choquet and Sugeno integrals in multi-criteria decision aid","authors":"Michel Grabisch, Christophe Labreuche","year":"2010","venue":"ANOR","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Grabisch et al., 2008] Michel Grabisch, Ivan Kojadinovic, and Patrick Meyer. A review of methods for capacity iden- tification in Choquet integral based multi-attribute utility theory. Eur. J. of Operational Res., 186(2):766-785, 2008.","title":"A review of methods for capacity identification in Choquet integral based multi-attribute utility theory","authors":"Michel Grabisch, Ivan Kojadinovic, Patrick Meyer","year":"2008","venue":"Eur. J. of Operational Res","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Grabisch, 1995] M. Grabisch. A new algorithm for identi- fying fuzzy measures and its application to pattern recog- nition. In FUZZ-IEEE-95, pages 145-150, 1995.","title":"A new algorithm for identifying fuzzy measures and its application to pattern recognition","authors":"M Grabisch","year":"1995","venue":"FUZZ-IEEE-95","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Grabisch, 1997] Michel Grabisch. K-order Additive Dis- crete Fuzzy Measures and Their Representation. Fuzzy Sets and Systems, 92:167-189, 1997.","title":"K-order Additive Discrete Fuzzy Measures and Their Representation","authors":"Michel Grabisch","year":"1997","venue":"Fuzzy Sets and Systems","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Havens and Anderson, 2018] Timothy C Havens and Derek T Anderson. Machine Learning of Choquet Integral Regression with Respect to a Bounded Capacity (or Non-monotonic Fuzzy Measure). In FUZZ-IEEE-18, 2018.","title":"Machine Learning of Choquet Integral Regression with Respect to a Bounded Capacity (or Non-monotonic Fuzzy Measure)","authors":"C Timothy, Derek T Havens, Anderson","year":"2018","venue":"FUZZ-IEEE-18","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Huang et al., 2008] Z. Huang, T.D. Gedeon, and M. Nikravesh. Pattern tree induction: A new ma- chine learning method. IEEE TFS, 16(4):958-970, 2008.","title":"Pattern tree induction: A new machine learning method","authors":"Z Huang, T D Gedeon, M Nikravesh","year":"2008","venue":"IEEE TFS","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Ioffe and Szegedy, 2015] S. Ioffe and C. Szegedy. Batch normalization: Accelerating deep network training by re- ducing internal covariate shift. In ICML-15, 2015.","title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","authors":"S Ioffe, C Szegedy","year":"2015","venue":"ICML-15","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Jang et al., 2017] Eric Jang, Shixiang Gu, and Ben Poole. Categorical reparameterization with gumbel-softmax. In Int. Conf. on Learning Representations ICLR. OpenRe- view.net, 2017.","title":"Categorical reparameterization with gumbel-softmax","authors":"Eric Jang, Shixiang Gu, Ben Poole","year":"2017","venue":"Int. Conf. on Learning Representations ICLR. OpenReview.net","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Krantz et al., 1971] D.H. Krantz, R.D. Luce, P. Suppes, and A. Tversky. Foundations of measurement: vol. 1, additive and polynomial representations. Academic Press, 1971.","title":"Foundations of measurement: vol. 1, additive and polynomial representations","authors":"D H Krantz, R D Luce, P Suppes, A Tversky","year":"1971","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Labreuche and Fossier, 2018] Christophe Labreuche and Simon Fossier. Explaining Multi-Criteria Decision Aid- ing Models with an Extended Shapley Value. In IJCAI, pages 331-339, 2018.","title":"Explaining Multi-Criteria Decision Aiding Models with an Extended Shapley Value","authors":"Fossier Labreuche, Christophe Labreuche, Simon Fossier","year":"2018","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2018/46"},{"position":22,"raw":"[Miller, 1956] George Abram Miller. The magical number seven plus or minus two: some limits on our capacity for processing information. Psychological review, 63 2:81- 97, 1956.","title":"The magical number seven plus or minus two: some limits on our capacity for processing information","authors":"George Abram Miller, Miller","year":"1956","venue":"Psychological review","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Senge and Hüllermeier, 2015] R. Senge and E. Hüllermeier. Fast fuzzy pattern tree learning for classification. IEEE Transactions on Fuzzy Systems, 23(6):2024-2033, 2015.","title":"Fast fuzzy pattern tree learning for classification","authors":"R Senge, E Hüllermeier","year":"2015","venue":"IEEE Transactions on Fuzzy Systems","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Senge and Hüllermeier, 2011] R Senge and E Hüllermeier. Top-Down Induction of Fuzzy Pattern Trees. IEEE Trans- actions on Fuzzy Systems, 19(2):241-252, 2011.","title":"Top-Down Induction of Fuzzy Pattern Trees","authors":"R Senge, Hüllermeier","year":"2011","venue":"IEEE Transactions on Fuzzy Systems","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Sobrie, 2016] Olivier Sobrie. Learning preferences with multiple-criteria models. PhD thesis, Univ. of Mons, 2016.","title":"Olivier Sobrie. Learning preferences with multiple-criteria models","authors":"Sobrie","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Wachsmuth et al., 2017] H. Wachsmuth, N. Naderi, Y. Hou, Y. Bilu, V. Prabhakaran, T.A. Thijm, G. Hirst, and B. Stein. Computational argumentation quality assessment in natu- ral language. In Proc. 15th Conf. of the European Chapter of the Ass. for Computational Linguistics, 2017.","title":"Computational argumentation quality assessment in natural language","authors":"H Wachsmuth, N Naderi, Y Hou, Y Bilu, V Prabhakaran, T A Thijm, G Hirst, B Stein","year":"2017","venue":"Proc. 15th Conf. of the European Chapter of the Ass. for Computational Linguistics","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}