Contrastive Learning Augmented Social Recommendations

TL;DR

This paper introduces a novel social recommendation method that uses contrastive learning and denoising strategies to improve interest representation, especially for cold users with limited interaction data.

Contribution

It proposes a dual-view denoising approach combined with mutual distillation to effectively leverage social graphs for enhanced recommendations.

Findings

Improves recommendation accuracy for cold users.

Effectively denoises social graphs using low-rank SVD.

Aligns social and behavioral interests through contrastive learning.

Abstract

Recommender systems are essential for modern content platforms, yet traditional behavior-based models often struggle with cold users who have limited interaction data. Engaging these users is crucial for platform growth. To bridge this gap, we propose leveraging the social-relation graph to enrich interest representations from behavior-based models. However, extracting value from social graphs is challenging due to relation noise and cross-domain inconsistency. To address the noise propagation and obtain accurate social interest, we employ a dual-view denoising strategy, employing low-rank SVD to the user-item interaction matrix for a denoised social graph and contrastive learning to align the original and reconstructed social graphs. Addressing the interest inconsistency between social and behavioral interests, we adopt a "mutual distillation" technique to isolate the original interests into aligned social/behavior interests and social/behavior specific interests, maximizing the utility of both. Experimental results on widely adopted industry datasets verify the method's effectiveness, particularly for cold users, offering a fresh perspective for future research. The implementation can be accessed at https://github.com/WANGLin0126/CLSRec.