| 摘要: |
| 对比学习是一种在计算机视觉和自然语言处理等领域广泛应用的自监督学习技术. 图对比学习指的是在图数据上应用对比学习技术的一类方法. 给出图对比学习的基本概念、算法和应用的一个综述. 首先介绍图对比学习的背景和意义及其在图数据上的基本概念; 然后详细阐述图对比学习的主流方法, 包括基于不同图数据增强策略的方法分类、基于不同图神经网络编码器结构的方法分类以及基于不同对比损失目标的方法分类等; 最后提出了3个图对比学习的研究思路. 研究结果表明, 图对比学习是一项有效的技术, 可以用来解决图数据上节点分类、图分类等一系列下游任务. |
| 关键词: 图对比学习 自监督学习 图分类 节点分类 图神经网络 |
| DOI：10.13328/j.cnki.jos.007417 |
| 分类号: |
| 基金项目:国家自然科学基金(62372264); 之江实验室软课题(K2023PD0AK01) |
|
| Survey on Graph Contrastive Learning Methods |
|
LIU Zi-Yang1, WANG Chao-Kun1, ZHANG Heng2
|
|
1.School of Software, Tsinghua University, Beijing 100084, China;2.Zhejiang Laboratory, Hangzhou 311121, China
|
| Abstract: |
| Contrastive learning is a self-supervised learning technique widely used in various fields such as computer vision and natural language processing. Graph contrastive learning (GCL) refers to methods that apply contrastive learning techniques to graph data. A review is presented on the basic concepts, methods, and applications of graph contrastive learning. First, the background and significance of GCL, as well as its basic concepts on graph data, are introduced. Then, the mainstream GCL methods are elaborated in detail, including methods with different graph data augmentation strategies, methods with different graph neural network (GNN) encoder structures, and methods with different contrastive loss objectives. Finally, three research ideas for GCL are proposed. Research findings demonstrate that graph contrastive learning is an effective approach for addressing various downstream tasks, including node classification and graph classification. |
| Key words: graph contrastive learning (GCL) self-supervised learning graph classification node classification graph neural network (GNN) |
