NeurIPS 2025
Faithful Group Shapley Value
Best Paper Award Honorable Mention · ICML 2025 DataWorld Workshop
Overview
Faithful Group Shapley Value addresses group-level data valuation when data providers contribute batches of data. The paper identifies a strategic group-splitting vulnerability in existing approaches and proposes a faithful valuation method with efficient approximation algorithms.
* Equal contribution
Citation
Lee, K., Liu, Z., Tang, W., and Zhang, Y. (2025). "Faithful Group Shapley Value." Advances in Neural Information Processing Systems (NeurIPS). ICML 2025 DataWorld Workshop Best Paper Award Honorable Mention.
More publications
All publications- NeurIPS · 2026 Generalized Priority-Aware Shapley Value
- ICML NExT-Game Workshop · 2026 First-Order Efficiency for Probabilistic Value Estimation via A Statistical Viewpoint
- ICML · 2026 Priority-Aware Shapley Value
- Journal of Applied Statistics · 2026 Bayesian Hierarchical Time-Varying Distributed Lag Nonlinear Model: Applications in the Short-Term Association between Ambient Temperature and Daily Confirmed Cases of COVID-19
- ICLR · 2025 Leave-One-Out Stable Conformal Prediction