{"type":"ScholarlyArticle","title":"The Shapley Value in Machine Learning","authors":[{"name":"Benedek Rozemberczki","slug":"benedek-rozemberczki","given":"Benedek","family":"Rozemberczki","affiliation":"Research Data & Analytics , Research & Development IT , AstraZeneca"},{"name":"Lauren Watson","slug":"lauren-watson","given":"Lauren","family":"Watson","affiliation":"The University of Edinburgh , School of Informatics"},{"name":"Péter Bayer","slug":"peter-bayer","given":"Péter","family":"Bayer","affiliation":"Toulouse School of Economics &"},{"name":"Hao-Tsung Yang","slug":"hao-tsung-yang","given":"Hao-Tsung","family":"Yang","affiliation":"The University of Edinburgh , School of Informatics"},{"name":"Olivér Kiss","slug":"oliver-kiss","given":"Olivér","family":"Kiss","affiliation":"Central European University , Department of Economics and Business"},{"name":"Sebastian Nilsson","slug":"sebastian-nilsson","given":"Sebastian","family":"Nilsson","affiliation":"Research Data & Analytics , Research & Development IT , AstraZeneca"},{"name":"Rik Sarkar","slug":"rik-sarkar","given":"Rik","family":"Sarkar","affiliation":"The University of Edinburgh , School of Informatics; Institute for Advanced Study in Toulouse"}],"abstract":"Over the last few years, the Shapley value, a solution concept from cooperative game theory, has found numerous applications in machine learning. In this paper, we first discuss fundamental concepts of cooperative game theory and axiomatic properties of the Shapley value. Then we give an overview of the most important applications of the Shapley value in machine learning: feature selection, explainability, multi-agent reinforcement learning, ensemble pruning, and data valuation. We examine the most crucial limitations of the Shapley value and point out directions for future research.","doi":"10.24963/ijcai.2022/778","url":"https://ijcai.org/proceedings/2022/778","pdf":"https://ijcai.org/proceedings/2022/0778.pdf","markdown":"https://ijcai.org/proceedings/2022/778.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/778","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Survey Track","track":"Survey Track","number":778,"pages":{"first":5572,"last":5579},"keywords":["Survey Track: Machine Learning","Survey Track: Constraint Satisfaction and Optimization","Survey Track: -","Survey Track: Data Mining"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38987278","length_sec":77,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38985421","length_sec":662,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Albizuri et al., 2006] Josune Albizuri, Jesús Aurrecoechea, et al. Configuration Values: Extensions of the Coalitional Owen Value. Games and Economic Behavior, pages 1-17, 2006.","title":"Josune Albizuri, Jesús Aurrecoechea, et al. Configuration Values: Extensions of the Coalitional Owen Value","authors":"Albizuri","year":"2006","venue":"Games and Economic Behavior","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Ancona et al., 2019] Marco Ancona, Cengiz Oztireli, and Markus Gross. Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Value Approxima- tion. In International Conference on Machine Learning, pages 272-281, 2019.","title":"Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Value Approximation","authors":"Marco Ancona, Cengiz Oztireli, Markus Gross","year":"2019","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Banzhaf III, 1964] John F Banzhaf III. Weighted Voting Doesn't Work: A Mathematical Analysis. Rutgers L. Rev., page 317, 1964.","title":"Weighted Voting Doesn't Work: A Mathematical Analysis","authors":"John F Banzhaf, Iii","year":"1964","venue":"Rutgers L. Rev","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Burgess et al., 2021] Mark A Burgess and Archie C Chapman. Approximating the Shapley Value Using Stratified Empirical Bernstein Sampling. International Joint Conferences on Artificial Intelligence Organization, 2021.","title":"Approximating the Shapley Value Using Stratified Empirical Bernstein Sampling","authors":"A Mark, Archie C Burgess, Chapman","year":"2021","venue":"International Joint Conferences on Artificial Intelligence Organization","doi":null,"url":null,"internal_url":"/proceedings/2021/11"},{"position":5,"raw":"[Castro et al., 2009] Javier Castro, Daniel Gómez, and Juan Tejada. Polynomial Calculation of the Shapley Value Based on Sampling. Computers & Operations Research, 36(5):1726- 1730, 2009.","title":"Polynomial Calculation of the Shapley Value Based on Sampling","authors":"Javier Castro, Daniel Gómez, Juan Tejada","year":"2009","venue":"Computers & Operations Research","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Castro et al., 2017] Javier Castro, Daniel Gómez, et al. Improv- ing Polynomial Estimation of the Shapley Value by Stratified Random Sampling with Optimum Allocation. Computers & Operations Research, 82:180-188, 2017.","title":"Improving Polynomial Estimation of the Shapley Value by Stratified Random Sampling with Optimum Allocation","authors":"Javier Castro, Daniel Gómez","year":"2017","venue":"Computers & Operations Research","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Chalkiadakis et al., 2011] Georgios Chalkiadakis, Edith Elkind, and Michael Wooldridge. Computational Aspects of Cooperative Game Theory. Synthesis Lectures on Artificial Intelligence and Machine Learning, 5(6):1-168, 2011.","title":"Computational Aspects of Cooperative Game Theory","authors":"Georgios Chalkiadakis, Edith Elkind, Michael Wooldridge","year":"2011","venue":"Synthesis Lectures on Artificial Intelligence and Machine Learning","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Chen et al., 2018] Jianbo Chen, Le Song, Martin Wainwright, and Michael Jordan. L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data. In International Conference on Learning Representations, 2018.","title":"Efficient Model Interpretation for Structured Data","authors":"Jianbo Chen, Le Song, Martin Wainwright, Michael Jordan, ; -Shapley, C-Shapley","year":"2018","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Cohen et al., 2007] Shay Cohen, Gideon Dror, and Eytan Rup- pin. Feature Selection via Coalitional Game Theory. Neural Computation, (7):1939-1961, 2007.","title":"Feature Selection via Coalitional Game Theory","authors":"Shay Cohen, Gideon Dror, Eytan Ruppin","year":"2007","venue":"Neural Computation","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Cook, 1977] R Dennis Cook. Detection of influential observa- tion in linear regression. Technometrics, 1977.","title":"Detection of influential observation in linear regression","authors":"Dennis Cook","year":"1977","venue":"Technometrics","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Covert et al., 2021] Ian Covert and Su-In Lee. Improving KernelSHAP: Practical Shapley Value Estimation Using Linear Regression. In International Conference on Artificial Intelligence and Statistics, pages 3457-3465, 2021.","title":"Ian Covert and Su-In Lee. Improving KernelSHAP: Practical Shapley Value Estimation Using Linear Regression","authors":"Covert","year":"2021","venue":"International Conference on Artificial Intelligence and Statistics","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Dasgupta et al., 2009] Anirban Dasgupta, Petros Drineas, , et al. Sampling algorithms and coresets for \\ell p regression. SIAM Journal on Computing, pages 2060-2078, 2009.","title":"Sampling algorithms and coresets for \\ell p regression","authors":"Anirban Dasgupta, Petros Drineas","year":"2009","venue":"SIAM Journal on Computing","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Deutch et al., 2021] Daniel Deutch, Nave Frost, Amir Gilad, and Oren Sheffer. Explanations for Data Repair Through Shapley Values, page 362-371. 2021.","title":"Explanations for Data Repair Through Shapley Values","authors":"Daniel Deutch, Nave Frost, Amir Gilad, Oren Sheffer","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Duval et al., 2021] Alexandre Duval and Fragkiskos D. Malliaros. Graphsvx: Shapley value explanations for graph neu- ral networks. In Machine Learning and Knowledge Discovery in Databases., pages 302-318, 2021.","title":"Graphsvx: Shapley value explanations for graph neural networks","authors":"Alexandre Duval, Fragkiskos D Malliaros","year":"2021","venue":"Machine Learning and Knowledge Discovery in Databases","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Fan et al., 2021] Zhenan Fan, Huang Fang, Zirui Zhou, et al. Improving Fairness for Data Valuation in Federated Learning. arXivv:2109.09046, 2021.","title":"Improving Fairness for Data Valuation in Federated Learning","authors":"Zhenan Fan, Huang Fang, Zirui Zhou","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Fatima et al., 2008] Shaheen S Fatima, Michael Wooldridge, and Nicholas R Jennings. A Linear Approximation Method for the Shapley Value. Artificial Intelligence, 172(14):1673-1699, 2008.","title":"A Linear Approximation Method for the Shapley Value","authors":"Michael Shaheen S Fatima, Nicholas R Wooldridge, Jennings","year":"2008","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Frye et al., 2020a] Christopher Frye, Damien de Mijolla, Tom Begley, et al. Shapley Explainability on the Data Manifold. In International Conference on Learning Representations, 2020.","title":"Shapley Explainability on the Data Manifold","authors":"Frye","year":"2020","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Frye et al., 2020b] Christopher Frye, Colin Rowat, and Ilya Feige. Asymmetric Shapley Values: Incorporating Causal Knowledge Into Model-Agnostic Explainability. Advances in Neural Information Processing Systems, 33, 2020.","title":"Asymmetric Shapley Values: Incorporating Causal Knowledge Into Model-Agnostic Explainability","authors":"Frye","year":"2020","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Fryer et al., 2021] Daniel Fryer, Inga Strümke, and Hien Nguyen. Shapley Values for Feature Selection: the Good, the Bad, and the Axioms. arXiv:2102.10936, 2021.","title":"Shapley Values for Feature Selection: the Good, the Bad, and the Axioms","authors":"Fryer","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Ghorbani et al., 2019] Amirata Ghorbani and James Zou. Data Shapley: Equitable Valuation of Data for Machine Learning. In International Conference on Machine Learning, pages 2242-2251, 2019.","title":"Data Shapley: Equitable Valuation of Data for Machine Learning","authors":"Ghorbani","year":"2019","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Ghorbani et al., 2020a] Amirata Ghorbani, Michael Kim, and James Zou. A Distributional Framework for Data Valuation. In International Conference on Machine Learning, pages 3535-3544, 2020.","title":"A Distributional Framework for Data Valuation","authors":"Ghorbani","year":"2020","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Ghorbani et al., 2020b] Amirata Ghorbani and James Zou. Neuron Shapley: Discovering the Responsible Neurons. In Advances in Neural Information Processing Systems, pages 5922-5932, 2020.","title":"Neuron Shapley: Discovering the Responsible Neurons","authors":"Ghorbani","year":"2020","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Guha et al., 2021] Ritam Guha, Ali Hussain Khan, et al. Cga: A new feature selection model for visual human action recogni- tion. Neural Computing and Applications, 33(10):5267-5286, 2021.","title":"Cga: A new feature selection model for visual human action recognition","authors":"Ritam Guha, Ali Hussain Khan","year":"2021","venue":"Neural Computing and Applications","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Guyon et al., 2003] Isabelle Guyon and André Elisseeff. An Introduction to Variable and Feature Selection. Journal of machine learning research, 3(Mar):1157-1182, 2003.","title":"An Introduction to Variable and Feature Selection","authors":"Isabelle Guyon, André Elisseeff","year":"2003","venue":"Journal of machine learning research","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Heskes et al., 2020] Tom Heskes, Evi Sijben, Ioan Gabriel Bucur, and Tom Claassen. Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Com- plex Models. Advances in Neural Information Processing Systems, 33, 2020.","title":"Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Models","authors":"Heskes","year":"2020","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Illés et al., 2019] Ferenc Illés and Péter Kerényi. Estimation of the Shapley Value by Ergodic Sampling. arXiv:1906.05224, 2019.","title":"Estimation of the Shapley Value by Ergodic Sampling","authors":"Illés","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Jia et al., 2019] Ruoxi Jia, David Dao, Boxin Wang, Hubis, et al. Towards Efficient Data Valuation Based on the Shapley Value. In The 22nd International Conference on Artificial Intelligence and Statistics, pages 1167-1176, 2019.","title":"Towards Efficient Data Valuation Based on the Shapley Value","authors":"Jia","year":"2019","venue":"The 22nd International Conference on Artificial Intelligence and Statistics","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Koh et al., 2017] Pang Wei Koh and Percy Liang. Under- standing black-box predictions via influence functions. In International Conference on Machine Learning, pages 1885- 1894, 2017.","title":"Understanding black-box predictions via influence functions","authors":"Pang Wei, Koh, Percy Liang","year":"2017","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Kumar et al., 2020] Elizabeth Kumar, Suresh Venkatasubrama- nian, Carlos Scheidegger, and Sorelle Friedler. Problems with Shapley-Value-Based Explanations as Feature Importance Measures. In International Conference on Machine Learning, pages 5491-5500, 2020.","title":"Problems with Shapley-Value-Based Explanations as Feature Importance Measures","authors":"Elizabeth Kumar, Suresh Venkatasubramanian, Carlos Scheidegger, Sorelle Friedler","year":"2020","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Kwon et al., 2021a] Yongchan Kwon, Manuel A Rivas, and James Zou. Efficient Computation and Analysis of Distri- butional Shapley Values. In International Conference on Artificial Intelligence and Statistics, pages 793-801, 2021.","title":"Efficient Computation and Analysis of Distributional Shapley Values","authors":"Kwon","year":"2021","venue":"International Conference on Artificial Intelligence and Statistics","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Kwon et al., 2021b] Yongchan Kwon and James Zou. Beta Shapley: a Unified and Noise-reduced Data Valuation Frame- work for Machine Learning. arXiv:2110.14049, 2021.","title":"Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learning","authors":"Kwon","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Li et al., 2021] Jiahui Li, Kun Kuang, Baoxiang Wang, et al. Shapley Counterfactual Credits for Multi-Agent Reinforcement Learning. In Proceedings of the 27th SIGKDD Conference on Knowledge Discovery & Data Mining, page 934-942, 2021.","title":"Shapley Counterfactual Credits for Multi-Agent Reinforcement Learning","authors":"Jiahui Li, Kun Kuang, Baoxiang Wang","year":"2021","venue":"Proceedings of the 27th SIGKDD Conference on Knowledge Discovery & Data Mining","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Liu et al., 2020] Yifei Liu, Chao Chen, Yazheng Liu, et al. Shapley Values and Meta-Explanations for Probabilistic Graph- ical Model Inference. In Proceedings of the 29th International Conference on Information & Knowledge Management, pages 945-954, 2020.","title":"Shapley Values and Meta-Explanations for Probabilistic Graphical Model Inference","authors":"Yifei Liu, Chao Chen, Yazheng Liu","year":"2020","venue":"Proceedings of the 29th International Conference on Information & Knowledge Management","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Liu et al., 2021] Zelei Liu, Yuanyuan Chen, Han Yu, Yang Liu, and Lizhen Cui. GTG-Shapley: Efficient and Accurate Participant Contribution Evaluation in Federated Learning. arXiv:2109.02053, 2021.","title":"GTG-Shapley: Efficient and Accurate Participant Contribution Evaluation in Federated Learning","authors":"Zelei Liu, Yuanyuan Chen, Han Yu, Yang Liu, Lizhen Cui","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Lomeli et al., 2019] Maria Lomeli, Mark Rowland, Arthur Gretton, and Zoubin Ghahramani. Antithetic and Monte Carlo Kernel Estimators for Partial Rankings. Statistics and Computing, pages 1127-1147, 2019.","title":"Antithetic and Monte Carlo Kernel Estimators for Partial Rankings","authors":"Maria Lomeli, Mark Rowland, Arthur Gretton, Zoubin Ghahramani","year":"2019","venue":"Statistics and Computing","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Lundberg et al., 2017] Scott M Lundberg and Su-In Lee. A Unified Approach to Interpreting Model Predictions. In Proceedings of the 31st International Conference on Neural Information Processing Systems, pages 4768-4777, 2017.","title":"A Unified Approach to Interpreting Model Predictions","authors":"M Scott, Su-In Lundberg, Lee","year":"2017","venue":"Proceedings of the 31st International Conference on Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Maleki et al., 2013] Sasan Maleki, Long Tran-Thanh, Greg Hines, Talal Rahwan, and Alex Rogers. Bounding the Estima- tion Error of Sampling-based Shapley Value Approximation. arXiv:1306.4265, 2013.","title":"Bounding the Estimation Error of Sampling-based Shapley Value Approximation","authors":"Sasan Maleki, Long Tran-Thanh, Greg Hines, Talal Rahwan, Alex Rogers","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Mitchell et al., 2021] Rory Mitchell, Joshua Cooper, Eibe Frank, and Geoffrey Holmes. Sampling Permutations for Shapley Value Estimation. arXiv:2104.12199, 2021.","title":"Sampling Permutations for Shapley Value Estimation","authors":"Rory Mitchell, Joshua Cooper, Eibe Frank, Geoffrey Holmes","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Okhrati et al., 2021] Ramin Okhrati and Aldo Lipani. A Mul- tilinear Sampling Algorithm to Estimate Shapley Values. In 2020 25th International Conference on Pattern Recognition (ICPR), pages 7992-7999. IEEE, 2021.","title":"A Multilinear Sampling Algorithm to Estimate Shapley Values","authors":"Okhrati","year":"2020","venue":"25th International Conference on Pattern Recognition (ICPR)","doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Owen, 1972] Guillermo Owen. Multilinear Extensions of Games. Management Science, 18(5-part-2):64-79, 1972.","title":"Guillermo Owen. Multilinear Extensions of Games","authors":"Owen","year":"1972","venue":"Management Science","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Owen, 1977] Guilliermo Owen. Values of Games with a Priori Unions. In Mathematical Economics and Game Theory, pages 76-88. 1977.","title":"Guilliermo Owen. Values of Games with a Priori Unions","authors":"Owen","year":"1977","venue":"Mathematical Economics and Game Theory","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Patel et al., 2021] Roma Patel, Marta Garnelo, Ian Gemp, et al. Game-Theoretic Vocabulary Selection via the Shapley Value and Banzhaf Index. In Proceedings of the 2021 Confer- ence of the North American Chapter of the Association for Computational Linguistics, pages 2789-2798, 2021.","title":"Game-Theoretic Vocabulary Selection via the Shapley Value and Banzhaf Index","authors":"Patel","year":"2021","venue":"Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[Pintér, 2011] Miklós Pintér. Regression games. Annals of Operations Research, 186(1):263-274, 2011.","title":"Miklós Pintér. Regression games","authors":"Pintér","year":"2011","venue":"Annals of Operations Research","doi":null,"url":null,"internal_url":null},{"position":44,"raw":"[Rozemberczki et al., 2021] Benedek Rozemberczki and Rik Sarkar. The Shapley Value of Classifiers in Ensemble Games. In Proceedings of the 30th International Conference on In- formation and Knowledge Management, page 1558-1567, 2021.","title":"Benedek Rozemberczki and Rik Sarkar. The Shapley Value of Classifiers in Ensemble Games","authors":"Rozemberczki","year":"2021","venue":"Proceedings of the 30th International Conference on Information and Knowledge Management","doi":null,"url":null,"internal_url":null},{"position":45,"raw":"[Rubinstein et al., 2016] Reuven Y Rubinstein and Dirk P Kroese. Simulation and the Monte Carlo Method. 2016.","title":"Simulation and the Monte Carlo Method","authors":"Y Reuven, Dirk P Rubinstein, Kroese","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":46,"raw":"[Shapley, 1953] Lloyd Shapley. A Value for N-Person Games. Contributions to the Theory of Games, pages 307-317, 1953.","title":"A Value for N-Person Games","authors":"Lloyd Shapley","year":"1953","venue":"Contributions to the Theory of Games","doi":null,"url":null,"internal_url":null},{"position":47,"raw":"[Shim et al., 2021] Dongsub Shim, Zheda Mai, Jihwan Jeong, Scott Sanner, et al. Online Class-Incremental Continual Learning with Adversarial Shapley Value. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 9630-9638, 2021.","title":"Online Class-Incremental Continual Learning with Adversarial Shapley Value","authors":"Shim","year":"2021","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":48,"raw":"[Singal et al., 2021] Raghav Singal, George Michailidis, and Hoiyi Ng. Flow-based Attribution in Graphical Models: A Recursive Shapley Approach. In Proceedings of the 38th International Conference on Machine Learning, volume 139, pages 9733-9743, 2021.","title":"Flow-based Attribution in Graphical Models: A Recursive Shapley Approach","authors":"Singal","year":"2021","venue":"Proceedings of the 38th International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":49,"raw":"[Sun et al., 2012] Xin Sun, Yanheng Liu, Jin Li, et al. Feature Evaluation and Selection with Cooperative Game Theory. Pattern recognition, 45(8):2992-3002, 2012.","title":"Feature Evaluation and Selection with Cooperative Game Theory","authors":"Xin Sun, Yanheng Liu, Jin Li","year":"2012","venue":"Pattern recognition","doi":null,"url":null,"internal_url":null},{"position":50,"raw":"[Sundararajan et al., 2020a] Mukund Sundararajan, Kedar Dhamdhere, and Ashish Agarwal. The Shapley Taylor Interaction Index. In International Conference on Machine Learning, pages 9259-9268, 2020.","title":"The Shapley Taylor Interaction Index","authors":"Sundararajan","year":"2020","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":51,"raw":"[Sundararajan et al., 2020b] Mukund Sundararajan and Amir Najmi. The Many Shapley Values for Model Explanation. In International Conference on Machine Learning, pages 9269-9278, 2020.","title":"The Many Shapley Values for Model Explanation","authors":"Sundararajan","year":"2020","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":52,"raw":"[Touati et al., 2021] Sofiane Touati, Mohammed Said Radjef, and SAIS Lakhdar. A Bayesian Monte Carlo Method for Computing the Shapley Value: Application to Weighted Voting and Bin Packing Games. Computers & Operations Research, 125:105094, 2021.","title":"A Bayesian Monte Carlo Method for Computing the Shapley Value: Application to Weighted Voting and Bin Packing Games","authors":"Sofiane Touati, Mohammed Said Radjef, Lakhdar","year":"2021","venue":"Computers & Operations Research","doi":null,"url":null,"internal_url":null},{"position":53,"raw":"[Tripathi et al., 2020] Sandhya Tripathi, N Hemachandra, and Prashant Trivedi. Interpretable Feature Subset Selection: A Shapley Value Based Approach. In IEEE International Conference on Big Data, pages 5463-5472, 2020.","title":"Interpretable Feature Subset Selection: A Shapley Value Based Approach","authors":"Sandhya Tripathi, Prashant Hemachandra, Trivedi","year":"2020","venue":"IEEE International Conference on Big Data","doi":null,"url":null,"internal_url":null},{"position":54,"raw":"[Wang et al., 2020] Tianhao Wang, Johannes Rausch, Ce Zhang, et al. A Principled Approach to Data Valuation for Federated Learning. In Federated Learning, pages 153-167. 2020.","title":"A Principled Approach to Data Valuation for Federated Learning","authors":"Tianhao Wang, Johannes Rausch, Ce Zhang","year":"2020","venue":"Federated Learning","doi":null,"url":null,"internal_url":null},{"position":55,"raw":"[Wang et al., 2021a] Jianhong Wang, Jinxin Wang, Yuan Zhang, Yunjie Gu, and Tae-Kyun Kim. SHAQ: Incorporating Shapley Value Theory into Q-Learning for Multi-Agent Reinforcement Learning. arXiv:2105.15013, 2021.","title":"SHAQ: Incorporating Shapley Value Theory into Q-Learning for Multi-Agent Reinforcement Learning","authors":"Wang","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":56,"raw":"[Wang et al., 2021b] Jiaxuan Wang, Jenna Wiens, and Scott Lundberg. Shapley Flow: A Graph-Based Approach to Inter- preting Model Predictions. In International Conference on Artificial Intelligence and Statistics, pages 721-729, 2021.","title":"Shapley Flow: A Graph-Based Approach to Interpreting Model Predictions","authors":"Wang","year":"2021","venue":"International Conference on Artificial Intelligence and Statistics","doi":null,"url":null,"internal_url":null},{"position":57,"raw":"[Williamson et al., 2020] Brian Williamson and Jean Feng. Ef- ficient Nonparametric Statistical Inference on Population Feature Importance Using Shapley Values. In International Conference on Machine Learning, pages 10282-10291, 2020.","title":"Efficient Nonparametric Statistical Inference on Population Feature Importance Using Shapley Values","authors":"Brian Williamson, Jean Feng","year":"2020","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":58,"raw":"[Winter, 1989] Eyal Winter. A Value for Cooperative Games with Levels Structure of Cooperation. International Journal of Game Theory, 18(2):227-40, 1989.","title":"A Value for Cooperative Games with Levels Structure of Cooperation","authors":"Eyal Winter","year":"1989","venue":"International Journal of Game Theory","doi":null,"url":null,"internal_url":null},{"position":59,"raw":"[Yan et al., 2021] Tom Yan and Ariel Procaccia. If You Like Shapley Then You Will Love the Core. Proceedings of the AAAI Conference, pages 5751-5759, 2021.","title":"If You Like Shapley Then You Will Love the Core","authors":"Yan","year":"2021","venue":"Proceedings of the AAAI Conference","doi":null,"url":null,"internal_url":null},{"position":60,"raw":"[Yuan et al., 2021] Hao Yuan, Haiyang Yu, Jie Wang, Kang Li, and Shuiwang Ji. On Explainability of Graph Neural Networks via Subgraph Explorations. In Proceedings of the 38th International Conference on Machine Learning, pages 12241-12252, 2021.","title":"On Explainability of Graph Neural Networks via Subgraph Explorations","authors":"Haiyang Hao Yuan, Jie Yu, Kang Wang, Shuiwang Li, Ji","year":"2021","venue":"Proceedings of the 38th International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":61,"raw":"[Zhang et al., 2021] Hao Zhang, Yichen Xie, Longjie Zheng, et al. Interpreting Multivariate Shapley Interactions in DNNs. In Proceedings of the AAAI Conference on Artificial Intelli- gence, volume 35, pages 10877-10886, 2021.","title":"Interpreting Multivariate Shapley Interactions in DNNs","authors":"Hao Zhang, Yichen Xie, Longjie Zheng","year":"2021","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}