Contrastive Learning Method for Sequential Recommendation based on Multi-Intention Disentanglement

TL;DR

This paper introduces MIDCL, a contrastive learning approach that uses variational auto-encoders to disentangle and leverage multiple user intentions for improved sequential recommendation accuracy and interpretability.

Contribution

It proposes a novel method combining contrastive learning and intention disentanglement using VAE to enhance sequential recommendation systems.

Findings

MIDCL outperforms existing baseline methods in experiments.

The approach provides more interpretable recommendation results.

It effectively captures and utilizes multiple user intentions.

Abstract

Sequential recommendation is one of the important branches of recommender system, aiming to achieve personalized recommended items for the future through the analysis and prediction of users' ordered historical interactive behaviors. However, along with the growth of the user volume and the increasingly rich behavioral information, how to understand and disentangle the user's interactive multi-intention effectively also poses challenges to behavior prediction and sequential recommendation. In light of these challenges, we propose a Contrastive Learning sequential recommendation method based on Multi-Intention Disentanglement (MIDCL). In our work, intentions are recognized as dynamic and diverse, and user behaviors are often driven by current multi-intentions, which means that the model needs to not only mine the most relevant implicit intention for each user, but also impair the influence from irrelevant intentions. Therefore, we choose Variational Auto-Encoder (VAE) to realize the disentanglement of users' multi-intentions. We propose two types of contrastive learning paradigms for finding the most relevant user's interactive intention, and maximizing the mutual information of positive sample pairs, respectively. Experimental results show that MIDCL not only has significant superiority over most existing baseline methods, but also brings a more interpretable case to the research about intention-based prediction and recommendation.