Contrastive Learning Augmented Social Recommendations

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Lin, Wang, Weisong, Xiao, Xuanji, Li, Qing
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917000386707456
author Wang, Lin
Wang, Weisong
Xiao, Xuanji
Li, Qing
author_facet Wang, Lin
Wang, Weisong
Xiao, Xuanji
Li, Qing
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_15695
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Contrastive Learning Augmented Social Recommendations
Wang, Lin
Wang, Weisong
Xiao, Xuanji
Li, Qing
Information Retrieval
Artificial Intelligence
Social and Information Networks
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.
title Contrastive Learning Augmented Social Recommendations
topic Information Retrieval
Artificial Intelligence
Social and Information Networks
url https://arxiv.org/abs/2502.15695