Priority-Aware Shapley Value

Kiljae Lee, Ziqi Liu, Weijing Tang, Yuan ZhangICML 2026 · OpenReview

Abstract

Shapley values are widely used for model-agnostic data valuation and feature attribution, yet they implicitly assume contributors are interchangeable. This can be problematic when contributors are dependent (e.g., reused/augmented data or causal feature orderings) or when contributions should be adjusted by factors such as trust or risk. We propose Priority-Aware Shapley Value (PASV), which incorporates both hard precedence constraints and soft, contributor-specific priority weights. PASV is applicable to general precedence structures, recovers precedence-only and weight-only Shapley variants as special cases, and is uniquely characterized by natural axioms. We develop an efficient adjacent-swap Metropolis–Hastings sampler for scalable Monte Carlo estimation and analyze limiting regimes induced by extreme priority weights. Experiments on data valuation (MNIST/CIFAR10) and feature attribution (Census Income) demonstrate more structure-faithful allocations and a practical sensitivity analysis via our proposed ``priority sweeping".
BibTeX
@inproceedings{lee2026priority,
  author = {Kiljae Lee and Ziqi Liu and Weijing Tang and Yuan Zhang},
  title = {{Priority-Aware Shapley Value}},
  booktitle = {International Conference on Machine Learning},
  year = {2026},
  url = {https://openreview.net/forum?id=uG4IOdaAGk},
}

Loading related content...

Figure