FastSHAP: Real-Time Shapley Value Estimation

Abstract

Shapley values are widely used to explain black-box models, but they are costly to calculate because they require many model evaluations. We introduce FastSHAP, a method for estimating Shapley values in a single forward pass using a learned explainer model. FastSHAP amortizes the cost of explaining many inputs via a learning approach inspired by the Shapley value's weighted least squares characterization, and it can be trained using standard stochastic gradient optimization. We compare FastSHAP to existing estimation approaches, revealing that it generates high-quality explanations with orders of magnitude speedup.

ICLR 2022 Camera Ready, 20 pages, 10 figures, 3 tables

References in corpus (7)

• fastai: A Layered API for Deep Learning
• Understanding Global Feature Contributions With Additive Importance Measures
• Feature relevance quantification in explainable AI: A causal problem
• Explaining by Removing: A Unified Framework for Model Explanation
• CXPlain: Causal Explanations for Model Interpretation under Uncertainty
• Restricting the Flow: Information Bottlenecks for Attribution
• Sampling Permutations for Shapley Value Estimation