提出新指标解释为何删边比加边更有效，改进图对比学习性能。
Why Does Dropping Edges Usually Outperform Adding Edges in Graph Contrastive Learning?
- 引入错误传播率（EPR）量化图结构适配网络程度
- 基于EPR权重同时进行加边和删边增强，提升表征质量
- 理论与实验结合，适合研究图学习增广机制的读者
图对比学习（GCL）作为图表示学习的有效自监督方法被广泛应用。然而，如何施加充分且稳定的图增强以生成合适的对比视图仍是关键问题。删边是当前GCL的主要增强方式，而加边因表现不稳定未被普遍采用。据我们所知，尚无理论分析解释为何删边通常优于加边。为此，本文提出新度量指标——错误传播率（EPR），用于量化图结构对网络的适应性。受理论结论及正向激励噪声思想启发，我们提出一种新型GCL算法：基于错误传播的图对比学习（EPAGCL），该算法基于EPR计算出的权重，同时使用加边和删边作为增强手段。在多个真实世界数据集上的大量实验验证了理论分析的正确性及所提算法的有效性。代码已公开于：https://github.com/hyzhang98/EPAGCL。
原文摘要 · Abstract (English)
Graph contrastive learning (GCL) has been widely used as an effective self-supervised learning method for graph representation learning. However, how to apply adequate and stable graph augmentation to generating proper views for contrastive learning remains an essential problem. Dropping edges is a primary augmentation in GCL while adding edges is not a common method due to its unstable performance. To our best knowledge, there is no theoretical analysis to study why dropping edges usually outperforms adding edges. To answer this question, we introduce a new metric, namely Error Passing Rate (EPR), to quantify how a graph fits the network. Inspired by the theoretical conclusions and the idea of positive-incentive noise, we propose a novel GCL algorithm, Error-PAssing-based Graph Contrastive Learning (EPAGCL), which uses both edge adding and edge dropping as its augmentations. To be specific, we generate views by adding and dropping edges based on the weights derived from EPR. Extensive experiments on various real-world datasets are conducted to validate the correctness of our theoretical analysis and the effectiveness of our proposed algorithm. Our code is available at: https://github.com/hyzhang98/EPAGCL.
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。