Dual-disentangle Framework for Diversified Sequential Recommendation

TL;DR

This paper introduces DDSRec, a framework that disentangles user interests and intentions to improve both diversity and accuracy in sequential recommendation systems.

Contribution

The paper proposes a novel model-agnostic dual-disentangle framework that enhances diversity without sacrificing accuracy in sequential recommendation tasks.

Findings

DDSRec outperforms existing methods in accuracy.

DDSRec improves recommendation diversity.

Experimental results validate the effectiveness of DDSRec.

Abstract

Sequential recommendation predicts user preferences over time and has achieved remarkable success. However, the growing length of user interaction sequences and the complex entanglement of evolving user interests and intentions introduce significant challenges to diversity. To address these, we propose a model-agnostic Dual-disentangle framework for Diversified Sequential Recommendation (DDSRec). The framework refines user interest and intention modeling by adopting disentangling perspectives in interaction modeling and representation learning, thereby balancing accuracy and diversity in sequential recommendations. Extensive experiments on multiple public datasets demonstrate the effectiveness and superiority of DDSRec in terms of accuracy and diversity for sequential recommendations.