[论文解读] XSimGCL: Towards Extremely Simple Graph Contrastive Learning for Recommendation

Junliang Yu, Xin Xia+4 more|arXiv (Cornell University)|Sep 6, 2022

Recommender Systems and Techniques被引用 29

一句话总结

XSimGCL 提出一种基于噪声、轻量级的图对比学习在推荐中的方法，其性能可与依赖增强的方法相媲美甚至超越，具有单向前向架构以提高效率。

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.

研究动机与目标

• 研究在基于对比学习的推荐中，图增强的作用以及对比损失如何塑造表示的均匀性。
• 提出一种简单的基于噪声的增强，用以可控地正则化嵌入的均匀性。
• 开发 XSimGCL，使推荐和对比任务在单个前向传播中统一。
• 提供关于跨层对比和共享表示的好处的理论与实证证据。

提出的方法

• 通过向嵌入添加受控的均匀噪声，引入基于噪声的表示增强。
• 提出 XSimGCL，它对推荐和对比任务使用相同的扰动表示，使得单次前向传播成为可能。
• 将最终层对比替换为跨层对比，以利用图谱中的高频信息。
• 使用联合损失，将 BPR 风格的推荐损失与基于 InfoNCE 的对比损失结合。
• 给出基于图谱的理论分析，以证明跨层对比的有效性。

Figure 1: Graph contrastive learning with edge dropout for recommendation.

实验结果

研究问题

• RQ1 图增强在基于对比学习的推荐模型中有多必要，它们对性能的实际贡献是什么？
• RQ2 表示层面的噪声增强能否控制学习到的嵌入的均匀性并提升推荐质量？
• RQ3 利用高频信息的跨层对比是否相较于最终层对比具有优势？
• RQ4 与基于增强的以及先前的简单对比学习方法相比，XSimGCL 在效率与准确性方面如何？

主要发现

• InfoNCE 驱动的均匀性，而非图增强，主要驱动基于对比学习的推荐性能提升。
• 基于噪声的增强可以可控地增加表示的均匀性，从而改善长尾项目的推荐。
• XSimGCL 以单次前向架构实现了具竞争力或更优的性能，与 SimGCL 及其他基于增强的方法相比，降低了训练成本。
• 使用图谱的理论分析支持跨层对比作为对高频信息更好的利用。
• 在四个大规模稀疏数据集上的实证结果显示，XSimGCL 在准确性和训练效率方面优于基于增强的对手。

Figure 2: The architectures of SimGCL and XSimGCL.