一种具有全局信号的生成式图对比学习模型
A Generative Graph Contrastive Learning Model with Global Signal
AI总结：
针对图对比学习中随机扰动导致结构偏差及样本对权重均等的问题，提出CSG2L框架，通过SVD增强模块和自适应重加权的局部-全局依赖学习模块，在基准数据集上优于现有方法。
摘要：
图对比学习（GCL）近年来因其通过自监督学习方式从图中学习复杂结构信息而受到广泛关注。然而，流行的GCL模型可能因不恰当的对比信号而遭受性能下降。具体而言，它们通常基于随机扰动生成增强视图，这由于引入噪声而导致本质结构有偏。此外，它们对困难样本对和容易样本对赋予相同权重，从而忽略了样本对重要性的差异。为解决这些问题，本研究提出了一种新颖的用于精确图学习的对比信号生成框架（CSG2L），其包含以下两点思想：a) 构建一个基于奇异值分解（SVD）的增强模块（SVD-aug），以获取全局交互并避免随机噪声扰动；b) 设计一个具有自适应重加权策略的局部-全局依赖学习模块（LGDL），该策略能够区分困难样本对和容易样本对的影响。在基准数据集上的大量实验表明，所提出的CSG2L优于最先进的基线方法。此外，CSG2L与多种图神经网络（GNNs）兼容。
英文摘要：
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.
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。
