提出新图对比学习框架，提升结构信息提取精度。
A Generative Graph Contrastive Learning Model with Global Signal
- 用SVD生成全局交互视图，避免随机噪声干扰
- 自适应重加权机制区分难易样本对重要性
- 兼容多种GNN，适用于复杂图结构建模
图对比学习（GCL）近年来受到广泛关注，因其可通过自监督方式学习图的复杂结构信息。然而，现有主流GCL模型可能因对比信号不当导致性能下降：通常基于随机扰动生成增强视图，引入噪声使关键结构失真；且对难样本与易样本对赋予相同权重，忽略其重要性差异。为此，本文提出一种新型对比信号生成框架CSG2L，包含两个核心设计：(a) 基于奇异值分解（SVD）的增强模块（SVD-aug），用于获取全局交互信息并避免随机噪声扰动；(b) 具有自适应重加权策略的局部-全局依赖学习模块（LGDL），可区分难易样本对的影响。在多个基准数据集上的大量实验表明，所提CSG2L优于当前最优基线方法。此外，CSG2L可与多种GNN模型兼容。
原文摘要 · Abstract (English)
Graph contrastive learning (GCL) has garnered significant attention recently since it learns complex structural information from graphs through self-supervised learning manner. However, prevalent GCL models may suffer from performance degradation due to inappropriate contrastive signals. Concretely, they commonly generate augmented views based on random perturbation, which leads to biased essential structures due to the introduction of noise. In addition, they assign equal weight to both hard and easy sample pairs, thereby ignoring the difference in importance of the sample pairs. To address these issues, this study proposes a novel Contrastive Signal Generative Framework for Accurate Graph Learning (CSG2L) with the following two-fold ideas: a) building a singular value decomposition (SVD)-directed augmented module (SVD-aug) to obtain the global interactions as well as avoiding the random noise perturbation; b) designing a local-global dependency learning module (LGDL) with an adaptive reweighting strategy which can differentiate the effects of hard and easy sample pairs. Extensive experiments on benchmark datasets demonstrate that the proposed CSG2L outperforms the state-of-art baselines. Moreover, CSG2L is compatible with a variety of GNNs.
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。