PolySHAP: Extending KernelSHAP with Interaction-Informed Polynomial Regression
This work addresses the computational intractability of exact Shapley value estimation, which requires exponentially many model evaluations and thus does not scale to high-dimensional feature spaces. To overcome this limitation, the authors propose PolySHAP, a novel approximation method that replaces the linear assumption in KernelSHAP with higher-order polynomial regression to better capture nonlinear feature interactions. Theoretical analysis reveals that second-order PolySHAP is equivalent to pairwise sampling, thereby providing rigorous justification for this previously heuristic approach. Extensive experiments across multiple benchmark datasets demonstrate that PolySHAP achieves significantly improved accuracy and consistency in Shapley value estimation compared to existing methods.