SGCL: Unifying Self-Supervised and Supervised Learning for Graph Recommendation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Weizhi, Yang, Liangwei, Song, Zihe, Zou, Henrry Peng, Xu, Ke, Zhu, Yuanjie, Yu, Philip S.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908454987235328
author Zhang, Weizhi
Yang, Liangwei
Song, Zihe
Zou, Henrry Peng
Xu, Ke
Zhu, Yuanjie
Yu, Philip S.
author_facet Zhang, Weizhi
Yang, Liangwei
Song, Zihe
Zou, Henrry Peng
Xu, Ke
Zhu, Yuanjie
Yu, Philip S.
contents Recommender systems (RecSys) are essential for online platforms, providing personalized suggestions to users within a vast sea of information. Self-supervised graph learning seeks to harness high-order collaborative filtering signals through unsupervised augmentation on the user-item bipartite graph, primarily leveraging a multi-task learning framework that includes both supervised recommendation loss and self-supervised contrastive loss. However, this separate design introduces additional graph convolution processes and creates inconsistencies in gradient directions due to disparate losses, resulting in prolonged training times and sub-optimal performance. In this study, we introduce a unified framework of Supervised Graph Contrastive Learning for recommendation (SGCL) to address these issues. SGCL uniquely combines the training of recommendation and unsupervised contrastive losses into a cohesive supervised contrastive learning loss, aligning both tasks within a single optimization direction for exceptionally fast training. Extensive experiments on three real-world datasets show that SGCL outperforms state-of-the-art methods, achieving superior accuracy and efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2507_13336
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SGCL: Unifying Self-Supervised and Supervised Learning for Graph Recommendation
Zhang, Weizhi
Yang, Liangwei
Song, Zihe
Zou, Henrry Peng
Xu, Ke
Zhu, Yuanjie
Yu, Philip S.
Information Retrieval
Recommender systems (RecSys) are essential for online platforms, providing personalized suggestions to users within a vast sea of information. Self-supervised graph learning seeks to harness high-order collaborative filtering signals through unsupervised augmentation on the user-item bipartite graph, primarily leveraging a multi-task learning framework that includes both supervised recommendation loss and self-supervised contrastive loss. However, this separate design introduces additional graph convolution processes and creates inconsistencies in gradient directions due to disparate losses, resulting in prolonged training times and sub-optimal performance. In this study, we introduce a unified framework of Supervised Graph Contrastive Learning for recommendation (SGCL) to address these issues. SGCL uniquely combines the training of recommendation and unsupervised contrastive losses into a cohesive supervised contrastive learning loss, aligning both tasks within a single optimization direction for exceptionally fast training. Extensive experiments on three real-world datasets show that SGCL outperforms state-of-the-art methods, achieving superior accuracy and efficiency.
title SGCL: Unifying Self-Supervised and Supervised Learning for Graph Recommendation
topic Information Retrieval
url https://arxiv.org/abs/2507.13336