PRINCE: Provider-side Interpretability with Counterfactual Explanations in Recommender Systems

Abstract

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.

WSDM 2020, 9 pages

References in corpus (5)

• Reinforcement Knowledge Graph Reasoning for Explainable Recommendation
• Neural Rating Regression with Abstractive Tips Generation for Recommendation
• Pixie: A System for Recommending 3+ Billion Items to 200+ Million Users in Real-Time
• Personalized Social Recommendations - Accurate or Private?
• Explaining Classification Models Built on High-Dimensional Sparse Data

Cited by in corpus (2)

• DECE: Decision Explorer with Counterfactual Explanations for Machine Learning Models
• From Intrinsic to Counterfactual: On the Explainability of Contextualized Recommender Systems