mlsanityData to 14 Oct 2026

Faithful Group Shapley Value

arXiv 2505.19013 ↗First posted 25 May 2025cs.LG cs.AI econ.GNcited by 2

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 23 of its 39 references that are in the map. First posted on arXiv 25 May 2025.

Builds on

23 of 39 references.

References · 23

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2020Scaling Laws for Neural Language Modelscited by 6,586
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  4. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
  5. 2019Data Shapley: Equitable Valuation of Data for Machine Learningcited by 629
  6. 2017Deep Learning Scaling is Predictable, Empiricallycited by 582
  7. 2015Train faster, generalize better: Stability of stochastic gradient descentcited by 552
  8. 2019Towards Efficient Data Valuation Based on the Shapley Valuecited by 281
  9. 2021Beta Shapley: a Unified and Noise-reduced Data Valuation Framework for Machine Learningcited by 165
  10. 2020Improving KernelSHAP: Practical Shapley Value Estimation via Linear Regressioncited by 154
  11. 2019Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithmscited by 148
  12. 2021GTG-Shapley: Efficient and Accurate Participant Contribution Evaluation in Federated Learningcited by 74
11 more
  1. 2021Shapley Counterfactual Credits for Multi-Agent Reinforcement Learningcited by 38
  2. 2024Provably Accurate Shapley Value Estimation via Leverage Score Samplingcited by 23
  3. 2021groupShapley: Efficient prediction explanation with Shapley values for feature groupscited by 21
  4. 2024An Economic Solution to Copyright Challenges of Generative AIcited by 18
  5. 2022Variance reduced Shapley value estimation for trustworthy data valuationcited by 16
  6. 2023A Note on "Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithms"cited by 11
  7. 2024One Sample Fits All: Approximating All Probabilistic Values Simultaneously and Efficientlycited by 9
  8. 2024A Survey on Data Marketscited by 7
  9. 2024Uncertainty Quantification of Data Shapley via Statistical Inferencecited by 2
  10. 2024Group Shapley Value and Counterfactual Simulations in a Structural Modelcited by 1
  11. 2025Group Shapley with Robust Significance Testing and Its Application to Bond Recovery Rate Predictioncited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Priority-Aware Shapley Valuecited by 2
  2. 2026SurrogateSHAP: Training-Free Contributor Attribution for Text-to-Image (T2I) Modelscited by 0