Re4: Learning to Re-contrast, Re-attend, Re-construct for Multi-interest Recommendation

TL;DR

Re4 introduces a backward flow mechanism in multi-interest recommendation models to improve the distinctness, semantic reflection, and consistency of user interest embeddings, leading to better recommendation performance.

Contribution

The paper proposes the Re4 framework that incorporates backward flows for re-contrast, re-attend, and re-construct to enhance multi-interest user representations in recommender systems.

Findings

Re4 improves the distinctness of interest embeddings.

Re4 enhances the semantic alignment with user interests.

Re4 outperforms baseline models on real-world datasets.

Abstract

Effectively representing users lie at the core of modern recommender systems. Since users' interests naturally exhibit multiple aspects, it is of increasing interest to develop multi-interest frameworks for recommendation, rather than represent each user with an overall embedding. Despite their effectiveness, existing methods solely exploit the encoder (the forward flow) to represent multiple aspects of interests. However, without explicit regularization, the interest embeddings may not be distinct from each other nor semantically reflect representative historical items. Towards this end, we propose the Re4 framework, which leverages the backward flow to reexamine each interest embedding. Specifically, Re4 encapsulates three backward flows, i.e., 1) Re-contrast, which drives each interest embedding to be distinct from other interests using contrastive learning; 2) Re-attend, which ensures the interest-item correlation estimation in the forward flow to be consistent with the criterion used in final recommendation; and 3) Re-construct, which ensures that each interest embedding can semantically reflect the information of representative items that relate to the corresponding interest. We demonstrate the novel forward-backward multi-interest paradigm on ComiRec, and perform extensive experiments on three real-world datasets. Empirical studies validate that Re4 helps to learn learning distinct and effective multi-interest representations.