The DOI matches its Crossref record; 51 of the 51 references it cites were found in a registry or an index.
The Shapley Value in Machine Learning
Open accessAbstract
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
A Unified Approach to Interpreting Model Predictions
Lundberg, S., & Lee, S.-I. (2017) · arXiv · doi:10.48550/arxiv.1705.07874 · Cited by 23,707
Gauriat, C.-M., Pencolé, Y., Ribot, P., & Brouillet, G. (2024) · HAL (Le Centre pour la Communication Scientifique Directe) · doi:10.4230/oasics.dx.2024.27 · Cited by 12,586
An introduction to variable and feature selection
GuyonIsabelle, & ElisseeffAndré (2003) · Journal of Machine Learning Research · doi:10.5555/944919.944968 · Cited by 7,715
Simulation and the Monte Carlo Method
Rubinstein, R. Y., & Kroese, D. P. (2016) · Wiley Series in Probability and Statistics · doi:10.1002/9781118631980 · Cited by 3,356 · cited 1×
“For example, Mitchell et al. [ 2021 ] uses the trapezoid rule to sample q at fixed intervals while Okhrati et al. [ 2021 ] proposes incorporating antithetic sampling as a variance reduction technique.”
MethodDetection of Influential Observation in Linear Regression
Cook, R. D. (1977) · Technometrics · doi:10.1080/00401706.1977.10489493 · Cited by 2,268
Understanding Black-box Predictions via Influence Functions
Koh, P. W., & Liang, P. (2017) · arXiv · doi:10.48550/arxiv.1703.04730 · Cited by 1,514
Polynomial calculation of the Shapley value based on sampling
Castro, J., Gómez, D., & Tejada, J. (2009) · Computers & Operations Research · doi:10.1016/j.cor.2008.04.004 · Cited by 601
On Explainability of Graph Neural Networks via Subgraph ExplorationsPreprint
Yuan, H., Yu, H., Wang, J., Li, K., & Ji, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.05152 · Cited by 443
Multilinear Extensions of Games
Owen, G. (1972) · Management Science · doi:10.1287/mnsc.18.5.64 · Cited by 425
Shapley values for feature selection: the good, the bad, and the axioms
Fryer, D., Strumke, I., & Nguyen, H. (2021) · IEEE Access · doi:10.1109/access.2021.3119110 · Cited by 347
Computational Aspects of Cooperative Game Theory
Chalkiadakis, G., Elkind, E., & Wooldridge, M. (2012) · Synthesis Lectures on Artificial Intelligence and Machine Learning · doi:10.1007/978-3-031-01558-8 · Cited by 337
Problems with Shapley-value-based explanations as feature importance measures
Kumar, I. E., Venkatasubramanian, S., Scheidegger, C., & Friedler, S. (2020) · arXiv · doi:10.48550/arxiv.2002.11097 · Cited by 228
L-Shapley and C-Shapley: Efficient Model Interpretation for Structured DataPreprint
Chen, J., Song, L., Wainwright, M. J., & Jordan, M. I. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.02610 · Cited by 221
A linear approximation method for the Shapley value
Fatima, S. S., Wooldridge, M., & Jennings, N. R. (2008) · Artificial Intelligence · doi:10.1016/j.artint.2008.05.003 · Cited by 219
Online Class-Incremental Continual Learning with Adversarial Shapley Value
Shim, D., Mai, Z., Jeong, J., Sanner, S., Kim, H., & Jang, J. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i11.17159 · Cited by 189
GraphSVX: Shapley Value Explanations for Graph Neural Networks
Duval, A., & Malliaros, F. D. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-86520-7_19 · Cited by 188
A Principled Approach to Data Valuation for Federated Learning
Wang, T., Rausch, J., Zhang, C., Jia, R., & Song, D. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-63076-8_11 · Cited by 177
Neuron Shapley: Discovering the Responsible NeuronsPreprint
Ghorbani, A., & Zou, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.09815 · Cited by 174
GTG-Shapley: Efficient and Accurate Participant Contribution Evaluation in Federated Learning
Liu, Z., Chen, Y., Yu, H., Liu, Y., & Cui, L. (2022) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3501811 · Cited by 170
Towards Efficient Data Valuation Based on the Shapley Value
Jia, R., Dao, D., Wang, B., Hubis, F. A., Hynes, N., Gürel, N. M., Li, B., Zhang, C., Song, D. X., & Spanos, C. J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.10275 · Cited by 168
Feature Selection via Coalitional Game Theory
Cohen, S., Dror, G., & Ruppin, E. (2007) · Neural Computation · doi:10.1162/neco.2007.19.7.1939 · Cited by 144
Efficient nonparametric statistical inference on population feature importance using Shapley values
Williamson, B. D., & Feng, J. (2020) · PubMed · doi:10.48550/arxiv.2006.09481 · Cited by 119
Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine LearningPreprint
Kwon, Y., & Zou, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.14049 · Cited by 117
Castro, J., Gómez, D., Molina, E., & Tejada, J. (2017) · Computers & Operations Research · doi:10.1016/j.cor.2017.01.019 · Cited by 116
Computational Aspects of Cooperative Game Theory
Wooldridge, M. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-22000-5_1 · Cited by 114
A Value for cooperative games with levels structure of cooperation
Winter, E. (1989) · International Journal of Game Theory · doi:10.1007/bf01268161 · Cited by 113
Sampling Algorithms and Coresets for $\ell_p$ Regression
Dasgupta, A., Petros Drineas, B., Harb, B., Kumar, R., & Mahoney, M. W. (2009) · SIAM Journal on Computing · doi:10.1137/070696507 · Cited by 112
Heskes, T., Sijben, E., Bucur, I. G., & Claassen, T. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.01625 · Cited by 106
Feature evaluation and selection with cooperative game theory
Sun, X., Liu, Y., Li, J., Zhu, J., Chen, H., & Liu, X. (2012) · Pattern Recognition · doi:10.1016/j.patcog.2012.02.001 · Cited by 95
Shapley Flow: A Graph-based Approach to Interpreting Model PredictionsPreprint
Wang, J., Wiens, J., & Lundberg, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.14592 · Cited by 85
A Multilinear Sampling Algorithm to Estimate Shapley Values
Okhrati, R., & Lipani, A. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412511 · Cited by 79
Efficient computation and analysis of distributional Shapley valuesPreprint
Kwon, Y., Rivas, M. A., & Zou, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.01357 · Cited by 79
Improving KernelSHAP: Practical Shapley Value Estimation Using Linear Regression
Covert, I., & Lee, S. (2021) · International Conference on Artificial Intelligence and Statistics · Cited by 73
Shapley Counterfactual Credits for Multi-Agent Reinforcement Learning
Li, J., Kuang, K., Wang, B., Liu, F., Chen, L., Wu, F. Q., & Xiao, J. (2021) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3447548.3467420 · Cited by 69
Bounding the Estimation Error of Sampling-based Shapley Value ApproximationPreprint
Maleki, S., Tran-Thanh, L., Hines, G., Rahwan, T., & Rogers, A. (2013) · arXiv (Cornell University) · doi:10.48550/arxiv.1306.4265 · Cited by 62
CGA: a new feature selection model for visual human action recognition
Guha, R., Khan, A. H., Singh, P. K., Sarkar, R., & Bhattacharjee, D. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-05297-5 · Cited by 62
Self-citationConfiguration values: Extensions of the coalitional Owen value
Albizuri, M. J., Aurrecoechea, J., & Zarzuelo, J. M. (2005) · Games and Economic Behavior · doi:10.1016/j.geb.2005.08.016 · Cited by 56
A Distributional Framework for Data ValuationPreprint
Ghorbani, A., Kim, M. P., & Zou, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.12334 · Cited by 54
Touati, S., Radjef, M. S., & Saïs, L. (2020) · Computers & Operations Research · doi:10.1016/j.cor.2020.105094 · Cited by 48
Interpreting Multivariate Shapley Interactions in DNNs
Zhang, H., Xie, Y., Zheng, L., Zhang, D., & Zhang, Q. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i12.17299 · Cited by 48
Interpretable feature subset selection: A Shapley value based approach
Tripathi, S., Hemachandra, N., & Trivedi, P. (2020) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata50022.2020.9378102 · Cited by 35
Antithetic and Monte Carlo kernel estimators for partial rankings
Lomelí, M., Rowland, M., Gretton, A., & Ghahramani, Z. (2019) · Statistics and Computing · doi:10.1007/s11222-019-09859-z · Cited by 28
Game-theoretic Vocabulary Selection via the Shapley Value and Banzhaf Index
Patel, R., Garnelo, M., Gemp, I., Dyer, C., & Bachrach, Y. (2021) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2021.naacl-main.223 · Cited by 25
Approximating the Shapley Value Using Stratified Empirical Bernstein Sampling
Burgess, M. A., & Chapman, A. C. (2021) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/11 · Cited by 25
Explanations for Data Repair Through Shapley Values
Deutch, D., Frost, N., Gilad, A., & Sheffer, O. (2021) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3459637.3482341 · Cited by 18
The Shapley Value of Classifiers in Ensemble Games
Rózemberczki, B., & Sarkar, R. (2021) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3459637.3482302 · Cited by 12
Self-citationFlow-Based Attribution in Graphical Models: A Recursive Shapley ApproachPreprint
Singal, R., Michailidis, G. C., & Ng, H. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3845526 · Cited by 7
Shapley Values and Meta-Explanations for Probabilistic Graphical Model Inference
Liu, Y., Chen, C., Liu, Y., Zhang, X., & Xie, S. (2020) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3340531.3411881 · Cited by 4
Improving Fairness for Data Valuation in Federated Learning.Preprint
Fan, Z., Huang, F., Zhou, Z., Pei, J., Friedlander, M. P., Liu, C., & Zhang, Y. (2021) · arXiv (Cornell University) · Cited by 4
SHAQ: Incorporating Shapley Value Theory into Q-Learning for Multi-Agent Reinforcement Learning.Preprint
Wang, J., Wang, J., Zhang, Y., Gu, Y., & Kim, T. (2021) · arXiv (Cornell University) · Cited by 2
Data Shapley: Equitable Valuation of Data for Machine Learning
Ghorbani, A., & Zou, J. (2019) · arXiv · doi:10.48550/arxiv.1904.02868
Cited by
Obtaining genetics insights from deep learning via explainable artificial intelligence
Novakovsky, G., Dexter, N., Libbrecht, M. W., Wasserman, W. W., & Mostafavi, S. (2023) · Nature Reviews Genetics · doi:10.1038/s41576-022-00532-2 · Cited by 386
Challenges and opportunities for artificial intelligence in auditing: Evidence from the field
Kokina, J., Blanchette, S., Davenport, T. H., & Pachamanova, D. (2025) · International Journal of Accounting Information Systems · doi:10.1016/j.accinf.2025.100734 · Cited by 375
Inferring gene regulatory networks from single-cell multiome data using atlas-scale external data
Yuan, Q., & Duren, Z. (2025) · Nature Biotechnology · doi:10.1038/s41587-024-02182-7 · Cited by 165
“The Shapley value measures the contribution of features in a machine-learning model and is widely used in algorithms such as deep learning, graphical models and reinforcement learning 85 .”
Zhan, S., Huang, L., Luo, G., Zheng, S., Gao, Z., & Chao, H.-C. (2025) · Electronics · doi:10.3390/electronics14132512 · Cited by 82
Dakhli, R., & Barhoumi, W. (2024) · 2024 IEEE/ACS 21st International Conference on Computer Systems and Applications (AICCSA) · doi:10.1109/aiccsa63423.2024.10912611 · Cited by 5
Metadata
- Authors
- Rozemberczki, B., Watson, L., Bayer, P., Yang, H.-T., Kiss, O., Nilsson, S., & Sarkar, R.
- Venue
- Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence
- Published
- 2022-07
- Pages
- 5572-5579
- OpenAlex
- W4285606919
- Cited by
- 296
- References
- 51
- FWCI
- 225.19
- Type
- conference paper
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.