PRINCE: Provider-side Interpretability with Counterfactual Explanations in Recommender Systems
This addresses the need for user trust in recommender systems by providing scrutable and actionable explanations, though it is incremental as it builds on prior work with a new perspective.
The paper tackles the problem of generating interpretable explanations for recommender systems by introducing PRINCE, a provider-side mechanism that defines explanations as minimal sets of user actions whose removal changes the recommendation, and it shows more compact explanations than baselines in experiments on real-world datasets.
Interpretable explanations for recommender systems and other machine learning models are crucial to gain user trust. Prior works that have focused on paths connecting users and items in a heterogeneous network have several limitations, such as discovering relationships rather than true explanations, or disregarding other users' privacy. In this work, we take a fresh perspective, and present PRINCE: a provider-side mechanism to produce tangible explanations for end-users, where an explanation is defined to be a set of minimal actions performed by the user that, if removed, changes the recommendation to a different item. Given a recommendation, PRINCE uses a polynomial-time optimal algorithm for finding this minimal set of a user's actions from an exponential search space, based on random walks over dynamic graphs. Experiments on two real-world datasets show that PRINCE provides more compact explanations than intuitive baselines, and insights from a crowdsourced user-study demonstrate the viability of such action-based explanations. We thus posit that PRINCE produces scrutable, actionable, and concise explanations, owing to its use of counterfactual evidence, a user's own actions, and minimal sets, respectively.