Towards Principled Learning for Re-ranking in Recommender Systems
This work addresses a foundational gap in re-ranking for recommender systems, which is critical for both academia and industry, though it appears incremental as it builds on existing attentive listwise modeling approaches.
The paper tackles the problem of missing principles to guide the learning process and measure output quality in re-ranking for recommender systems, proposing convergence consistency and adversarial consistency principles that improve performance across various baseline methods and datasets.
As the final stage of recommender systems, re-ranking presents ordered item lists to users that best match their interests. It plays such a critical role and has become a trending research topic with much attention from both academia and industry. Recent advances of re-ranking are focused on attentive listwise modeling of interactions and mutual influences among items to be re-ranked. However, principles to guide the learning process of a re-ranker, and to measure the quality of the output of the re-ranker, have been always missing. In this paper, we study such principles to learn a good re-ranker. Two principles are proposed, including convergence consistency and adversarial consistency. These two principles can be applied in the learning of a generic re-ranker and improve its performance. We validate such a finding by various baseline methods over different datasets.