PEAR: Personalized Re-ranking with Contextualized Transformer for Recommendation

TL;DR

PEAR is a personalized re-ranking model utilizing contextualized transformers that captures complex item interactions and user context, significantly improving recommendation quality over existing methods.

Contribution

Introduces PEAR, a novel transformer-based re-ranking approach that models feature, item, and context interactions for personalized recommendations.

Findings

PEAR outperforms previous re-ranking models on public datasets.

Incorporating list-level satisfaction assessment improves ranking quality.

Experimental results demonstrate PEAR's superior effectiveness.

Abstract

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.