Preference-based and local post-hoc explanations for recommender systems
作者:
Highlights:
• Formal definitions of an explanation instance and interpretable features.
• In-depth study of locality and perturbation mechanism around an explanation instance.
• Model agnostic post-hoc linear explanation model with pointwise loss.
• Extension of linear-based explanation based on pairwise preference loss.
• Extensive experiments with 4 recommenders and up to 20M ratings.
摘要
•Formal definitions of an explanation instance and interpretable features.•In-depth study of locality and perturbation mechanism around an explanation instance.•Model agnostic post-hoc linear explanation model with pointwise loss.•Extension of linear-based explanation based on pairwise preference loss.•Extensive experiments with 4 recommenders and up to 20M ratings.
论文关键词:Post-hoc explanation,Recommender systems,Locality,Pairwise preference
论文评审过程:Received 10 July 2021, Revised 26 January 2022, Accepted 12 March 2022, Available online 15 March 2022, Version of Record 12 May 2022.
论文官网地址:https://doi.org/10.1016/j.is.2022.102021