Prediction via Shapley Value Regression
This addresses the inference-time efficiency problem for users of explainable AI by offering a novel approach to compute Shapley values without post-hoc overhead.
The paper tackles the computational cost of post-hoc Shapley value computation for model explanations by proposing ViaSHAP, a method that learns a function to compute Shapley values directly, enabling predictions via summation. Results show ViaSHAP performs on par with state-of-the-art algorithms for tabular data and provides significantly more accurate explanations than FastSHAP on tabular data and images.
Shapley values have several desirable, theoretically well-supported, properties for explaining black-box model predictions. Traditionally, Shapley values are computed post-hoc, leading to additional computational cost at inference time. To overcome this, a novel method, called ViaSHAP, is proposed, that learns a function to compute Shapley values, from which the predictions can be derived directly by summation. Two approaches to implement the proposed method are explored; one based on the universal approximation theorem and the other on the Kolmogorov-Arnold representation theorem. Results from a large-scale empirical investigation are presented, showing that ViaSHAP using Kolmogorov-Arnold Networks performs on par with state-of-the-art algorithms for tabular data. It is also shown that the explanations of ViaSHAP are significantly more accurate than the popular approximator FastSHAP on both tabular data and images.