XSimGCL: Towards Extremely Simple Graph Contrastive Learning for Recommendation

TL;DR

XSimGCL introduces a simple noise-based augmentation for graph contrastive learning in recommendation systems, effectively improving performance by promoting uniform representations and reducing reliance on complex graph augmentations.

Contribution

The paper proposes XSimGCL, a straightforward noise-based augmentation method that outperforms traditional graph augmentation techniques in contrastive recommendation models.

Findings

XSimGCL outperforms graph augmentation-based methods in accuracy.

It enhances representation uniformity and reduces popularity bias.

The method improves training efficiency significantly.

Abstract

Contrastive learning (CL) has recently been demonstrated critical in improving recommendation performance. The underlying principle of CL-based recommendation models is to ensure the consistency between representations derived from different graph augmentations of the user-item bipartite graph. This self-supervised approach allows for the extraction of general features from raw data, thereby mitigating the issue of data sparsity. Despite the effectiveness of this paradigm, the factors contributing to its performance gains have yet to be fully understood. This paper provides novel insights into the impact of CL on recommendation. Our findings indicate that CL enables the model to learn more evenly distributed user and item representations, which alleviates the prevalent popularity bias and promoting long-tail items. Our analysis also suggests that the graph augmentations, previously considered essential, are relatively unreliable and of limited significance in CL-based recommendation. Based on these findings, we put forward an eXtremely Simple Graph Contrastive Learning method (XSimGCL) for recommendation, which discards the ineffective graph augmentations and instead employs a simple yet effective noise-based embedding augmentation to generate views for CL. A comprehensive experimental study on four large and highly sparse benchmark datasets demonstrates that, though the proposed method is extremely simple, it can smoothly adjust the uniformity of learned representations and outperforms its graph augmentation-based counterparts by a large margin in both recommendation accuracy and training efficiency. The code and used datasets are released at https://github.com/Coder-Yu/SELFRec.