LoRA-NCL: Neighborhood-Enriched Contrastive Learning with Low-Rank Dimensionality Reduction for Graph Collaborative Filtering

Cao, Tianruo; Chen, Honghui; Hao, Zepeng; Hu, Tao

doi:10.3390/math11163577

Open AccessArticle

LoRA-NCL: Neighborhood-Enriched Contrastive Learning with Low-Rank Dimensionality Reduction for Graph Collaborative Filtering

Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha 410073, China

^*

Author to whom correspondence should be addressed.

Mathematics 2023, 11(16), 3577; https://doi.org/10.3390/math11163577

Submission received: 12 July 2023 / Revised: 9 August 2023 / Accepted: 17 August 2023 / Published: 18 August 2023

Download Versions Notes

Abstract

Graph Collaborative Filtering (GCF) methods have emerged as an effective recommendation approach, capturing users’ preferences over items by modeling user–item interaction graphs. However, these methods suffer from data sparsity in real scenarios, and their performance can be improved using contrastive learning. In this paper, we propose an optimized method, named LoRA-NCL, for GCF based on Neighborhood-enriched Contrastive Learning (NCL) and low-rank dimensionality reduction. We incorporate low-rank features obtained through matrix factorization into the NCL framework and employ LightGCN to extract high-dimensional representations. Extensive experiments on five public datasets demonstrate that the proposed method outperforms a competitive graph collaborative filtering base model, achieving 4.6% performance gains on the MovieLens dataset, respectively.

Keywords: Contrastive Learning; low-rank dimensionlity reduction; Graph Collaborative Filtering

Share and Cite

MDPI and ACS Style

Cao, T.; Chen, H.; Hao, Z.; Hu, T. LoRA-NCL: Neighborhood-Enriched Contrastive Learning with Low-Rank Dimensionality Reduction for Graph Collaborative Filtering. Mathematics 2023, 11, 3577. https://doi.org/10.3390/math11163577

AMA Style

Cao T, Chen H, Hao Z, Hu T. LoRA-NCL: Neighborhood-Enriched Contrastive Learning with Low-Rank Dimensionality Reduction for Graph Collaborative Filtering. Mathematics. 2023; 11(16):3577. https://doi.org/10.3390/math11163577

Chicago/Turabian Style

Cao, Tianruo, Honghui Chen, Zepeng Hao, and Tao Hu. 2023. "LoRA-NCL: Neighborhood-Enriched Contrastive Learning with Low-Rank Dimensionality Reduction for Graph Collaborative Filtering" Mathematics 11, no. 16: 3577. https://doi.org/10.3390/math11163577

APA Style

Cao, T., Chen, H., Hao, Z., & Hu, T. (2023). LoRA-NCL: Neighborhood-Enriched Contrastive Learning with Low-Rank Dimensionality Reduction for Graph Collaborative Filtering. Mathematics, 11(16), 3577. https://doi.org/10.3390/math11163577

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

LoRA-NCL: Neighborhood-Enriched Contrastive Learning with Low-Rank Dimensionality Reduction for Graph Collaborative Filtering

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI