SHAP values via sparse Fourier representation

NeurIPSSpotlight2025

Authors
Ali Gorji, Andisheh Amrollahi, Andreas Krause
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

SHAP (SHapley Additive exPlanations) values are a widely used method for local feature attribution in interpretable and explainable AI…

Opening excerpt from the authors’ abstract. source

Read the paper

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive