A Comprehensive Study of Shapley Value in Data Analytics
Not on the map. Why?
Abstract (arXiv)
Over the recent years, Shapley value (SV), a solution concept from cooperative game theory, has found numerous applications in data analytics (DA). This paper presents the first comprehensive study of SV used throughout the DA workflow, clarifying the key variables in defining DA-applicable SV and the essential functionalities that SV can provide for data scientists. We condense four primary challenges of using SV in DA, namely computation efficiency, approximation error, privacy preservation, and interpretability, disentangle the resolution techniques from existing arts in this field, then analyze and discuss the techniques w.r.t. each challenge and the potential conflicts between challenges.We also implement SVBench, a modular and extensible open-source framework for developing SV applications in different DA tasks, and conduct extensive evaluations to validate our analyses and discussions. Based on the qualitative and quantitative results, we identify the limitations of current efforts for applying SV to DA and highlight the directions of future research and engineering.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 77 of its 192 references that are in the map. First posted on arXiv 2 Dec 2024.
Builds on
77 of 192 references.
References · 77
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
- 2017Learning Important Features Through Propagating Activation Differencescited by 1,454
- 2019Data Shapley: Equitable Valuation of Data for Machine Learningcited by 617
- 2014OpenML: networked science in machine learningcited by 523
- 2019The many Shapley values for model explanationcited by 341
- 2019Towards Efficient Data Valuation Based on the Shapley Valuecited by 279
- 2019Explaining individual predictions when features are dependent: More accurate approximations to Shapley valuescited by 205
- 2020Improving KernelSHAP: Practical Shapley Value Estimation via Linear Regressioncited by 153
- 2019Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithmscited by 147
- 2020A Survey of Privacy Attacks in Machine Learningcited by 143
- 2020A Principled Approach to Data Valuation for Federated Learningcited by 127
- 2020True to the Model or True to the Data?cited by 123
38 more
- 2021FastSHAP: Real-Time Shapley Value Estimationcited by 123
- 2019Explaining Deep Neural Networks with a Polynomial Time Algorithm for Shapley Values Approximationcited by 115
- 2022Algorithms to estimate Shapley value feature attributionscited by 114
- 2021Sampling Permutations for Shapley Value Estimationcited by 101
- 2022The Shapley Value in Machine Learningcited by 97
- 2024The rising costs of training frontier AI modelscited by 91
- 2020Shapley explainability on the data manifoldcited by 88
- 2020A Distributional Framework for Data Valuationcited by 79
- 2019Measure Contribution of Participants in Federated Learningcited by 78
- 2018A Marketplace for Data: An Algorithmic Solutioncited by 75
- 2020TimeSHAP: Explaining Recurrent Models through Sequence Perturbationscited by 73
- 2021GTG-Shapley: Efficient and Accurate Participant Contribution Evaluation in Federated Learningcited by 73
- 2020Collaborative Machine Learning with Incentive-Aware Model Rewardscited by 71
- 2021GraphSVX: Shapley Value Explanations for Graph Neural Networkscited by 63
- 2020Efficient nonparametric statistical inference on population feature importance using Shapley valuescited by 61
- 2021Shapley values for feature selection: The good, the bad, and the axiomscited by 54
- 2021Shapley Explanation Networkscited by 41
- 2021Few-shot Backdoor Defense Using Shapley Estimationcited by 40
- 2020FedCoin: A Peer-to-Peer Payment System for Federated Learningcited by 39
- 2020A Survey on Data Pricing: from Economics to Data Sciencecited by 39
- 2020Efficient computation and analysis of distributional Shapley valuescited by 38
- 2018Model-based Pricing for Machine Learning in a Data Marketplacecited by 37
- 2021Explaining a Series of Models by Propagating Shapley Valuescited by 37
- 2021Shapley Counterfactual Credits for Multi-Agent Reinforcement Learningcited by 37
- 2022WeightedSHAP: analyzing and improving Shapley based feature attributionscited by 36
- 2023Explaining Predictive Uncertainty with Information Theoretic Shapley Valuescited by 36
- 2021Game of Gradients: Mitigating Irrelevant Clients in Federated Learningcited by 35
- 2023Approximating the Shapley Value without Marginal Contributionscited by 34
- 2019Interpret Federated Learning with Shapley Valuescited by 33
- 2020A Multilinear Sampling Algorithm to Estimate Shapley Valuescited by 33
- 2022CS-Shapley: Class-wise Shapley Values for Data Valuation in Classificationcited by 32
- 2024Beyond TreeSHAP: Efficient Computation of Any-Order Shapley Interactions for Tree Ensemblescited by 30
- 2024Rethinking Data Shapley for Data Selection Tasks: Misleads and Meritscited by 29
- 2021Fast TreeSHAP: Accelerating SHAP Value Computation for Treescited by 28
- 2021Data Shapley Valuation for Efficient Batch Active Learningcited by 27
- 2023Explaining Reinforcement Learning with Shapley Valuescited by 26
- 2021Collective eXplainable AI: Explaining Cooperative Strategies and Agent Contribution in Multiagent Reinforcement Learning with Shapley Valuescited by 24
- 2019The Shapley Value of Tuples in Query Answeringcited by 23
50 most cited of 77 All 77 (JSON)
Built on by
Citing papers per year: 2026: 2.
2 papers.