PEAR: Personalized Re-ranking with Contextualized Transformer for Recommendation
This work addresses the need for more accurate personalized recommendations by improving re-ranking, though it appears incremental as it builds on existing transformer-based methods.
The paper tackles the problem of re-ranking in recommender systems by introducing PEAR, a personalized model that captures feature-level, item-level, and contextual interactions from initial and historical lists, and includes a list-level classification task. Experimental results show superior effectiveness compared to previous models on public and production datasets.
The goal of recommender systems is to provide ordered item lists to users that best match their interests. As a critical task in the recommendation pipeline, re-ranking has received increasing attention in recent years. In contrast to conventional ranking models that score each item individually, re-ranking aims to explicitly model the mutual influences among items to further refine the ordering of items given an initial ranking list. In this paper, we present a personalized re-ranking model (dubbed PEAR) based on contextualized transformer. PEAR makes several major improvements over the existing methods. Specifically, PEAR not only captures feature-level and item-level interactions, but also models item contexts from both the initial ranking list and the historical clicked item list. In addition to item-level ranking score prediction, we also augment the training of PEAR with a list-level classification task to assess users' satisfaction on the whole ranking list. Experimental results on both public and production datasets have shown the superior effectiveness of PEAR compared to the previous re-ranking models.