为什么在图对比学习中删除边通常优于添加边？
Why Does Dropping Edges Usually Outperform Adding Edges in Graph Contrastive Learning?
AI总结：
本文提出错误传递率（EPR）解释图对比学习中删边通常优于加边的原因，并据此设计同时使用加边与删边的 EPAGCL 算法。
摘要：
图对比学习（GCL）作为一种用于图表示学习的有效自监督学习方法，已得到广泛应用。然而，如何应用充分且稳定的图增强来为对比学习生成合适的视图，仍然是一个关键问题。删除边是 GCL 中的一种主要增强方式，而添加边由于性能不稳定，并不是一种常用方法。据我们所知，目前尚无理论分析研究为什么删除边通常优于添加边。为回答这一问题，我们引入了一个新指标，即错误传递率（EPR），用于量化图与网络的拟合程度。受理论结论和正向激励噪声思想的启发，我们提出了一种新颖的 GCL 算法——基于错误传递的图对比学习（EPAGCL），该算法同时使用添加边和删除边作为其增强方式。具体而言，我们根据由 EPR 得到的权重，通过添加和删除边来生成视图。我们在多个真实世界数据集上进行了大量实验，以验证理论分析的正确性和所提算法的有效性。我们的代码可在 https://github.com/hyzhang98/EPAGCL 获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
