Faithful Group Shapley Value
Kiljae Lee, Ziqi Liu, Weijing Tang, Yuan Zhang

TL;DR
This paper introduces Faithful Group Shapley Value (FGSV), a new data valuation method that defends against strategic group splitting attacks and offers fast, accurate approximations for group data contributions.
Contribution
We propose FGSV, a novel group data valuation method that is robust to shell company attacks and includes an efficient approximation algorithm.
Findings
FGSV effectively defends against shell company attacks.
Our algorithm outperforms existing methods in speed and accuracy.
Empirical results confirm FGSV's faithful and reliable group valuation.
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
Taxonomy
TopicsEconomic theories and models
