Stabilizing Estimates of Shapley Values with Control Variates
This addresses the problem of unstable model explanations for ML practitioners, offering an incremental improvement to existing sampling methods.
The paper tackles the high computational cost and uncertainty in Shapley value approximations for explaining blackbox ML models by proposing ControlSHAP, a control variates-based method that reduces Monte Carlo variability without extra computation, achieving dramatic reductions in variability on high-dimensional datasets.
Shapley values are among the most popular tools for explaining predictions of blackbox machine learning models. However, their high computational cost motivates the use of sampling approximations, inducing a considerable degree of uncertainty. To stabilize these model explanations, we propose ControlSHAP, an approach based on the Monte Carlo technique of control variates. Our methodology is applicable to any machine learning model and requires virtually no extra computation or modeling effort. On several high-dimensional datasets, we find it can produce dramatic reductions in the Monte Carlo variability of Shapley estimates.