发现图推荐中对比学习的局限，提出更优的权重更新方法
Rethinking Contrastive Learning for Graph Collaborative Filtering: Limitations and a Simple Remedy
- 通过分析邻居对权重更新机制，揭示对比学习失效原因
- 新方法NT-SSM在多个数据集上显著提升推荐效果
- 适合研究图神经网络与推荐系统融合的开发者
图协同过滤（GCF）是推荐系统主流范式，广泛采用对比学习（CL）目标如采样软最大值（SSM）损失进行优化。然而，CL如何与GCF预测机制相互作用仍不明确。通过展开GCF预测机制，我们发现用户-物品预测分数由大量由用户与物品多跳邻居构成的邻居对的可学习权重聚合而成。这一分析表明，有效优化关键在于训练过程中哪些邻居对被加权。实验发现，仅选择结构上与目标用户和物品相似的一小部分邻居对进行加权即可实现有效推荐，且不同类型的邻居对加权效果差异显著。基于此，我们分析了SSM并识别其在邻居对权重更新动态中的关键缺陷。为此，我们提出NT-SSM，一种有效且原理清晰的对比学习目标，能诱导类型感知的邻居对权重更新动态。实验表明，在多个数据集和GCF模型上，NT-SSM均持续优于SSM。
原文摘要 · Abstract (English)
Graph collaborative filtering (GCF) is a dominant paradigm in recommender systems, where contrastive learning (CL) objectives such as the Sampled Softmax (SSM) loss are widely used for optimization. However, it remains unclear how CL interacts with the prediction mechanism of GCF. By unfolding the prediction mechanism of GCF, we show that the user-item prediction score is computed by aggregating learnable weights over a large number of neighbor pairs formed by the multi-hop neighbors of the user and the item. This analysis suggests that effective optimization critically depends on which neighbor pairs are upweighted during training. Empirically, we find that effective recommendation is achievable by selectively upweighting only a small subset of neighbor pairs whose constituent neighbors are structurally similar to the target user and item, and that the effect of such selective upweighting varies across different neighbor pair types. Based on these findings, we analyze SSM and identify key limitations in its neighbor pair weight update dynamics. To address these limitations, we propose NT-SSM, an effective and principled CL objective that induces type-aware neighbor pair weight update dynamics. Experiments demonstrate consistent performance improvements over SSM across multiple datasets and GCF models.
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。