Faithful Group Shapley Value

2025-05-25

AI Summary

Existing group-level data valuation methods—such as Group Shapley—are vulnerable to “shell-company attacks,” wherein adversaries artificially split data groups to inflate valuations. Method: This paper introduces the first strategy-proof group Shapley value (FGSV), provably resistant to such manipulative group splittings, and establishes its uniqueness and theoretical robustness guarantees. To address computational intractability, we design an efficient approximation algorithm leveraging novel mathematical properties of FGSV, integrating importance sampling with variance reduction techniques. Contribution/Results: Experiments demonstrate that our method significantly outperforms state-of-the-art approaches in valuation fidelity, computational efficiency, and scalability—particularly under large-scale batch data provisioning scenarios—while maintaining robustness against strategic manipulation.

Technology Category

• Game Theory and Economic Paradigms: Fair Division
• Machine Learning: Privacy
• Multiagent Systems: Mechanism Design

Application Category

• Security and Privacy: Data transparency and provenance
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Data Shapley is an important tool for data valuation, which quantifies the contribution of individual data points to machine learning models. In practice, group-level data valuation is desirable when data providers contribute data in batch. However, we identify that existing group-level extensions of Data Shapley are vulnerable to shell company attacks, where strategic group splitting can unfairly inflate valuations. We propose Faithful Group Shapley Value (FGSV) that uniquely defends against such attacks. Building on original mathematical insights, we develop a provably fast and accurate approximation algorithm for computing FGSV. Empirical experiments demonstrate that our algorithm significantly outperforms state-of-the-art methods in computational efficiency and approximation accuracy, while ensuring faithful group-level valuation.

Problem

• Addresses vulnerability of group-level Data Shapley to shell company attacks
• Proposes Faithful Group Shapley Value for fair group data valuation
• Develops fast approximation algorithm for accurate FGSV computation

Innovation

• Defends against shell company attacks
• Fast accurate approximation algorithm
• Ensures faithful group valuation