FastSHAP: Real-Time Shapley Value Estimation
2021-07-15ICLR 2022Code Available1· sign in to hype
Neil Jethani, Mukund Sudarshan, Ian Covert, Su-In Lee, Rajesh Ranganath
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/iancovert/fastshapOfficialIn paperpytorch★ 104
- github.com/neiljethani/fastshapOfficialIn papertf★ 10
- github.com/iclr1814/fastshapOfficialIn papertf★ 3
- github.com/tml-tuebingen/nshapnone★ 19
- github.com/davidenapolitano/bonespytorch★ 5
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.