CGCL：无需手工图数据增强的协作图对比学习
CGCL: Collaborative Graph Contrastive Learning without Handcrafted Graph Data Augmentations
AI总结：
本文提出协作图对比学习框架CGCL，通过多个互补图编码器观察图并以其特征作为对比视图，避免手工图增强带来的不稳定扰动，从而提升无监督图级表示学习性能。
摘要：
无监督图表示学习是一个非平凡课题。对比方法在结构化数据上的无监督表示学习中取得的成功，激发了在图上的类似尝试。现有的图对比学习（GCL）旨在学习多个增强视图之间的不变性，这使其严重依赖手工设计的图增强。然而，不恰当的图数据增强可能潜在地破坏这种不变性。在本文中，我们展示了不恰当增强的潜在危害，然后提出了一种新颖的协作图对比学习框架（CGCL）。该框架利用多个图编码器来观察图。从不同编码器观察到的特征作为对比学习中的对比视图，这避免了引入不稳定的扰动并保证了不变性。为确保不同图编码器之间的协作，我们提出了非对称架构和互补编码器的概念作为设计原则。为了进一步证明其合理性，我们分别利用两个定量指标来衡量CGCL的组装。大量实验证明了CGCL在无监督图级表示学习中的优势以及协作框架的潜力。用于可复现性的源代码可在 https://github.com/zhangtia16/CGCL 获取。
英文摘要：
Unsupervised graph representation learning is a non-trivial topic. The success of contrastive methods in the unsupervised representation learning on structured data inspires similar attempts on the graph. Existing graph contrastive learning (GCL) aims to learn the invariance across multiple augmentation views, which renders it heavily reliant on the handcrafted graph augmentations. However, inappropriate graph data augmentations can potentially jeopardize such invariance. In this paper, we show the potential hazards of inappropriate augmentations and then propose a novel Collaborative Graph Contrastive Learning framework (CGCL). This framework harnesses multiple graph encoders to observe the graph. Features observed from different encoders serve as the contrastive views in contrastive learning, which avoids inducing unstable perturbation and guarantees the invariance. To ensure the collaboration among diverse graph encoders, we propose the concepts of asymmetric architecture and complementary encoders as the design principle. To further prove the rationality, we utilize two quantitative metrics to measure the assembly of CGCL respectively. Extensive experiments demonstrate the advantages of CGCL in unsupervised graph-level representation learning and the potential of collaborative framework. The source code for reproducibility is available at https://github.com/zhangtia16/CGCL
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。
