不靠数据增强，用图网络邻层自然对比提升推荐效果
NLGCL: Naturally Existing Neighbor Layers Graph Contrastive Learning for Recommendation
- 利用GNN邻层节点作为正负样本对，无需额外数据增强
- 在4个公开数据集上超越现有方法，效率显著提升
- 适合追求高效高精度推荐系统的开发者使用
图神经网络（GNN）广泛用于协同过滤以捕捉用户与物品的高阶关系。为缓解推荐系统中的数据稀疏问题，图对比学习（GCL）通过最大化对比视图间的互信息成为有前景的方法。然而，现有GCL方法依赖引入语义无关噪声的数据增强技术，导致计算与存储成本过高，限制了其有效性与效率。为此，我们提出NLGCL，一种基于GNN邻层间天然对比视图的新框架。将每个节点及其下一层邻居视为正样本对，其余节点作为负样本，该方法避免了增强带来的噪声，同时保持语义相关性。此范式省去了耗时的视图构建与存储，实现高效计算，适用于真实场景。在四个公开数据集上的大量实验表明，NLGCL在效果与效率上均优于当前最优基线。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。