A Comprehensive Study of Shapley Value in Data Analytics

Abstract

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.

Accepted by VLDB 2025

References in corpus (19)

• OpenML: networked science in machine learning
• Explaining a Series of Models by Propagating Shapley Values
• A Survey of Privacy Attacks in Machine Learning
• TimeSHAP: Explaining Recurrent Models through Sequence Perturbations
• Improving Fairness for Data Valuation in Horizontal Federated Learning
• Shapley Counterfactual Credits for Multi-Agent Reinforcement Learning
• Transparent Contribution Evaluation for Secure Federated Learning on Blockchain
• A Comparative Study of Methods for Estimating Conditional Shapley Values and When to Use Them
• Greedy Shapley Client Selection for Communication-Efficient Federated Learning
• The Shapley Value in Database Management
• Efficient nonparametric statistical inference on population feature importance using Shapley values
• A feature selection method based on Shapley values robust to concept shift in regression
• Explaining Predictive Uncertainty with Information Theoretic Shapley Values
• Beyond TreeSHAP: Efficient Computation of Any-Order Shapley Interactions for Tree Ensembles
• Shapley values for cluster importance: How clusters of the training data affect a prediction
• FedSV: Byzantine-Robust Federated Learning via Shapley Value
• CS-Shapley: Class-wise Shapley Values for Data Valuation in Classification
• DU-Shapley: A Shapley Value Proxy for Efficient Dataset Valuation
• Computing the Relative Value of Spatio-Temporal Data in Wholesale and Retail Data Marketplaces