Skip to yearly menu bar Skip to main content


Poster

FastSHAP: Real-Time Shapley Value Estimation

Neil Jethani · Mukund Sudarshan · Ian Covert · Su-In Lee · Rajesh Ranganath

Keywords: [ interpretability ] [ explainability ] [ game theory ]


Abstract:

Although Shapley values are theoretically appealing for explaining black-box models, they are costly to calculate and thus impractical in settings that involve large, high-dimensional models. To remedy this issue, we introduce FastSHAP, a new method for estimating Shapley values in a single forward pass using a learned explainer model. To enable efficient training without requiring ground truth Shapley values, we develop an approach to train FastSHAP via stochastic gradient descent using a weighted least-squares objective function. In our experiments with tabular and image datasets, we compare FastSHAP to existing estimation approaches and find that it generates accurate explanations with an orders-of-magnitude speedup.

Chat is not available.