Better Late Than Never: Formulating and Benchmarking Recommendation Editing
This work addresses the need for efficient correction of recommendation errors to enhance user experience, presenting an incremental advancement by formalizing and benchmarking a new task in recommendation systems.
The paper tackles the problem of unsuitable recommendations in online platforms by introducing recommendation editing, a task that modifies known unsuitable behaviors without retraining, and demonstrates its effectiveness through a benchmark with novel evaluation metrics and a method achieving competitive results.
Recommendation systems play a pivotal role in suggesting items to users based on their preferences. However, in online platforms, these systems inevitably offer unsuitable recommendations due to limited model capacity, poor data quality, or evolving user interests. Enhancing user experience necessitates efficiently rectify such unsuitable recommendation behaviors. This paper introduces a novel and significant task termed recommendation editing, which focuses on modifying known and unsuitable recommendation behaviors. Specifically, this task aims to adjust the recommendation model to eliminate known unsuitable items without accessing training data or retraining the model. We formally define the problem of recommendation editing with three primary objectives: strict rectification, collaborative rectification, and concentrated rectification. Three evaluation metrics are developed to quantitatively assess the achievement of each objective. We present a straightforward yet effective benchmark for recommendation editing using novel Editing Bayesian Personalized Ranking Loss. To demonstrate the effectiveness of the proposed method, we establish a comprehensive benchmark that incorporates various methods from related fields. Codebase is available at https://github.com/cycl2018/Recommendation-Editing.