Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Priority-Aware Shapley Value

About

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".

Kiljae Lee, Ziqi Liu, Weijing Tang, Yuan Zhang• 2026

Related benchmarks

TaskDatasetResultRank
Data ValuationCIFAR10
Provider Influence (Mean)0.508
48
Data ValuationMNIST
Mean Valuation0.527
48
Showing 2 of 2 rows

Other info

Follow for update