LAC：连续空间中可学习增强的图对比学习
LAC: Graph Contrastive Learning with Learnable Augmentation in Continuous Space
AI总结：
本文提出图对比学习框架 LAC，通过在正交连续空间中进行可学习的数据增强，并结合 InfoBal 信息论原则设计 pretext 任务，在无监督节点表示学习中显著超越现有方法。
摘要：
图对比学习框架已在生成高质量节点表示方面展现出成功。现有关于高效数据增强方法和图对比学习理想 pretext 任务的研究仍然有限，导致无监督设置下节点表示不够理想。本文提出 LAC，一个在正交连续空间中具有可学习数据增强的图对比学习框架。为了在增强过程中捕获图数据中的代表性信息，我们引入连续视图增强器，该增强器同时应用掩码拓扑增强模块和跨通道特征增强模块，分别在正交连续空间内自适应增强拓扑信息和特征信息。连续空间的正交性确保增强过程避免维度坍缩。为提升 pretext 任务的有效性，我们提出名为 InfoBal 的信息论原则，并引入相应的 pretext 任务。这些任务使连续视图增强器能够在视图间保持代表性信息的一致性，同时最大化视图间的多样性，并允许编码器在无监督设置中充分利用代表性信息。实验结果表明，LAC 显著优于当前最先进的框架。
英文摘要：
Graph Contrastive Learning frameworks have demonstrated success in generating high-quality node representations. The existing research on efficient data augmentation methods and ideal pretext tasks for graph contrastive learning remains limited, resulting in suboptimal node representation in the unsupervised setting. In this paper, we introduce LAC, a graph contrastive learning framework with learnable data augmentation in an orthogonal continuous space. To capture the representative information in the graph data during augmentation, we introduce a continuous view augmenter, that applies both a masked topology augmentation module and a cross-channel feature augmentation module to adaptively augment the topological information and the feature information within an orthogonal continuous space, respectively. The orthogonal nature of continuous space ensures that the augmentation process avoids dimension collapse. To enhance the effectiveness of pretext tasks, we propose an information-theoretic principle named InfoBal and introduce corresponding pretext tasks. These tasks enable the continuous view augmenter to maintain consistency in the representative information across views while maximizing diversity between views, and allow the encoder to fully utilize the representative information in the unsupervised setting. Our experimental results show that LAC significantly outperforms the state-of-the-art frameworks.
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。
