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.
Complete list of metadatas

Cited literature [60 references]  Display  Hide  Download

https://hal.inria.fr/hal-02433443
Contributor : Oana Balalau <>
Submitted on : Thursday, January 9, 2020 - 10:16:01 AM
Last modification on : Saturday, February 1, 2020 - 1:55:44 AM

File

2020-hal-pixie.pdf
Files produced by the author(s)

Licence


Copyright

Identifiers

  • HAL Id : hal-02433443, version 1

Citation

Azin Ghazimatin, Oana Balalau, Rishiraj Saha, Gerhard Weikum. PRINCE: Provider-side Interpretability with Counterfactual Explanations in Recommender Systems. WSDM 2020 - 13th ACM International Conference on Web Search and Data Mining, Feb 2020, Houston, Texas, United States. ⟨hal-02433443⟩

Share

Metrics

Record views

21

Files downloads

273