Explaining Preferences with Shapley Values
This work addresses the underexplored problem of preference explanation, which is important for users and practitioners in machine learning, but it appears incremental as it builds on existing Shapley value methods.
The paper tackles the challenge of explaining preferences in machine learning by proposing Pref-SHAP, a Shapley value-based framework for pairwise comparison data, and demonstrates that it provides richer and more insightful explanations than baselines on synthetic and real-world datasets.
While preference modelling is becoming one of the pillars of machine learning, the problem of preference explanation remains challenging and underexplored. In this paper, we propose \textsc{Pref-SHAP}, a Shapley value-based model explanation framework for pairwise comparison data. We derive the appropriate value functions for preference models and further extend the framework to model and explain \emph{context specific} information, such as the surface type in a tennis game. To demonstrate the utility of \textsc{Pref-SHAP}, we apply our method to a variety of synthetic and real-world datasets and show that richer and more insightful explanations can be obtained over the baseline.