NLGCL: Naturally Existing Neighbor Layers Graph Contrastive Learning for Recommendation

TL;DR

NLGCL introduces a neighbor-layer-based contrastive learning method for GNNs in recommendation systems, improving efficiency and effectiveness by avoiding augmentation noise and reducing computational costs.

Contribution

The paper proposes NLGCL, a novel contrastive learning framework that leverages naturally existing neighbor layers in GNNs, eliminating the need for data augmentation.

Findings

NLGCL outperforms state-of-the-art methods on four datasets.

NLGCL reduces computational and storage costs.

NLGCL enhances recommendation accuracy and efficiency.

Abstract

Graph Neural Networks (GNNs) are widely used in collaborative filtering to capture high-order user-item relationships. To address the data sparsity problem in recommendation systems, Graph Contrastive Learning (GCL) has emerged as a promising paradigm that maximizes mutual information between contrastive views. However, existing GCL methods rely on augmentation techniques that introduce semantically irrelevant noise and incur significant computational and storage costs, limiting effectiveness and efficiency. To overcome these challenges, we propose NLGCL, a novel contrastive learning framework that leverages naturally contrastive views between neighbor layers within GNNs. By treating each node and its neighbors in the next layer as positive pairs, and other nodes as negatives, NLGCL avoids augmentation-based noise while preserving semantic relevance. This paradigm eliminates costly view construction and storage, making it computationally efficient and practical for real-world scenarios. Extensive experiments on four public datasets demonstrate that NLGCL outperforms state-of-the-art baselines in effectiveness and efficiency.