From Abstract to Actionable: Pairwise Shapley Values for Explainable AI
This addresses the need for more transparent and scalable XAI methods in high-stakes domains, representing an incremental improvement over existing Shapley value techniques.
The paper tackled the problem of limited interpretability and scalability in Shapley value approximations for explainable AI by proposing Pairwise Shapley Values, which ground feature attributions in explicit comparisons between data instances, enhancing interpretability across regression and classification scenarios like real estate pricing and drug discovery.
Explainable AI (XAI) is critical for ensuring transparency, accountability, and trust in machine learning systems as black-box models are increasingly deployed within high-stakes domains. Among XAI methods, Shapley values are widely used for their fairness and consistency axioms. However, prevalent Shapley value approximation methods commonly rely on abstract baselines or computationally intensive calculations, which can limit their interpretability and scalability. To address such challenges, we propose Pairwise Shapley Values, a novel framework that grounds feature attributions in explicit, human-relatable comparisons between pairs of data instances proximal in feature space. Our method introduces pairwise reference selection combined with single-value imputation to deliver intuitive, model-agnostic explanations while significantly reducing computational overhead. Here, we demonstrate that Pairwise Shapley Values enhance interpretability across diverse regression and classification scenarios--including real estate pricing, polymer property prediction, and drug discovery datasets. We conclude that the proposed methods enable more transparent AI systems and advance the real-world applicability of XAI.