Contrastive Learning (CL) is one of the most popular self-supervised learning frameworks for graph representation learning, which trains a Graph Neural Network (GNN) by discriminating positive and negative node pairs. However, there are two challenges for CL on graphs. On the one hand, traditional CL methods will unavoidably introduce semantic errors since they will treat some semantically similar nodes as negative pairs. On the other hand, most of the existing CL methods ignore the multiplexity nature of the real-world graphs, where nodes are connected by various relations and each relation represents a view of the graph. To address these challenges, we propose a novel Graph Multi-View Prototypical (Graph-MVP) framework to extract node embeddings on multiplex graphs. Firstly, we introduce a Graph Prototypical Contrastive Learning (Graph-PCL) framework to capture both node-level and semantic-level information for each view of multiplex graphs. Graph-PCL captures the node-level information by a simple yet effective data transformation technique. It captures the semantic-level information by an Expectation-Maximization (EM) algorithm, which alternatively performs clustering over node embeddings and parameter updating for GNN. Next, we introduce Graph-MVP based on Graph-PCL to jointly model different views of the multiplex graphs. Our key insight behind Graph-MVP is that different view-specific embeddings of the same node should have similar underlying semantic, based on which we propose two versions of Graph-MVP: Graph-MVP_hard and Graph-MVP_soft to align embeddings across views. Finally, we evaluate the proposed Graph-PCL and Graph-MVP on a variety of real-world datasets and downstream tasks. The experimental results demonstrate the effectiveness of the proposed Graph-PCL and Graph-MVP frameworks.
翻译:对比学习( CL) 是用于图形演示学习的最受欢迎的自我监督的学习框架之一。 它通过区分正和负节点来训练图形神经网络( GNN) 。 然而, 在图形中 CL 存在两个挑战。 一方面, 传统的 CL 方法将不可避免地引入语义错误, 因为它们会把一些语义相似的节点作为负对。 另一方面, 现有的 CL 方法大多忽略了真实世界图形的多维度性质, 其节点通过各种关系连接, 每一个关系代表图形的视图。 为了应对这些挑战, 我们提议了一个新型的 图形多维 Protocl( Graph- MVP) 框架, 以提取多维点点P 的多维点的 直径的多维点P 。 我们现有的 CL 方法会忽略了数字的节点级信息, 以简单而有效的数据流流流技术来更新 GMVIL 的多维值 。