Skip to main navigation Skip to search Skip to main content

LLMGCL: graph contrastive learning with Large Language Models for recommendation

  • Shiqi Ge
  • , Shunmei Meng*
  • , Jielong Zhou
  • , Lianyong Qi
  • , Xiaolong Xu
  • , Xuyun Zhang
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

Abstract

Contrastive Learning (CL) has recently achieved significant progress in the field of recommender systems, as it leverages supervision signals from raw data to mitigate the issue of data sparsity. However, most existing methods rely on random or heuristic data augmentation strategies, which often disrupt the intrinsic structural relationships in the graph and introduce spurious connections, leading to suboptimal representations for recommendation tasks. To address these challenges, we propose a novel graph contrastive learning model based on Large Language Model (LLM), named LLMGCL, which leverages LLM for both embedding augmentation and graph augmentation, and incorporates inter-layer contrastive learning to improve recommendation performance. Specifically, the proposed method first designs an LLM-driven embedding augmentation strategy, where item embeddings pre-trained by LLM are aggregated to construct user embeddings, enabling contrastive views to retain richer semantic relationships. Furthermore, to enhance the structural integrity of the graph while minimizing noise, we develop two targeted graph augmentation strategies powered by LLM: one leverages LLM to identify high-confidence user-item interactions from historical behaviors to refine observed preferences, while the other infers potential but unobserved interactions to reinforce graph connectivity. Finally, we design an inter-layer contrastive learning module that aligns representations across different Graph Neural Network layers, effectively mitigating the over-smoothing effect and enhancing feature discrimination. These combined strategies significantly improve recommendation quality, as demonstrated by extensive experiments on public datasets.

Original languageEnglish
Title of host publicationIEEE ICWS 2025
Subtitle of host publicationProceedings of the 2025 IEEE International Conference on Web Services
EditorsRong N. Chang, Carl K. Chang, Jingwei Yang, Nimanthi Atukorala, Dan Chen, Sumi Helal, Sasu Tarkoma, Qiang He, Tevfik Kosar, Claudio Agostino Ardagna, Amin Beheshti, Bo Cheng, Walid Gaaloul
Place of PublicationPiscataway, NJ
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages48-57
Number of pages10
Edition2025
ISBN (Electronic)9798331555634
ISBN (Print)9798331555641
DOIs
Publication statusPublished - 2025
Event2025 IEEE International Conference on Web Services, ICWS 2025 - Helsinki, Finland
Duration: 7 Jul 2025 → 12 Jul 2025

Publication series

NameProceedings of the IEEE International Conference on Web Services
ISSN (Print)2836-3876
ISSN (Electronic)2836-3868

Conference

Conference2025 IEEE International Conference on Web Services, ICWS 2025
Country/TerritoryFinland
CityHelsinki
Period7/07/25 → 12/07/25

Keywords

  • contrastive learning
  • data augmentation
  • GNN
  • LLM
  • recommender systems

Fingerprint

Dive into the research topics of 'LLMGCL: graph contrastive learning with Large Language Models for recommendation'. Together they form a unique fingerprint.

Cite this