AdaptiveRec: Adaptively Construct Pairs for Contrastive Learning in Sequential Recommendation

TL;DR

This paper introduces AdaptiveRec, a novel contrastive learning method for sequential recommendation that adaptively constructs pairs to improve item embeddings and reduce false negatives, leading to better recommendation performance.

Contribution

The paper proposes an adaptive pair construction strategy for contrastive learning in sequential recommendation, addressing false negatives and enhancing embedding quality.

Findings

Improved recommendation accuracy over existing methods

Effective reduction of false negative issues

Versatile applicability across different recommendation scenarios

Abstract

This paper presents a solution to the challenges faced by contrastive learning in sequential recommendation systems. In particular, it addresses the issue of false negative, which limits the effectiveness of recommendation algorithms. By introducing an advanced approach to contrastive learning, the proposed method improves the quality of item embeddings and mitigates the problem of falsely categorizing similar instances as dissimilar. Experimental results demonstrate performance enhancements compared to existing systems. The flexibility and applicability of the proposed approach across various recommendation scenarios further highlight its value in enhancing sequential recommendation systems.