Deep Graph Contrastive Representation Learning
This addresses the problem of learning effective graph representations without labels for applications in graph-structured data analysis, representing a strong incremental advance in contrastive methods.
The paper tackles unsupervised graph representation learning by proposing a node-level contrastive framework that generates two graph views through corruption and maximizes agreement between node representations, achieving state-of-the-art performance with large margins and even surpassing supervised methods on transductive tasks.
Graph representation learning nowadays becomes fundamental in analyzing graph-structured data. Inspired by recent success of contrastive methods, in this paper, we propose a novel framework for unsupervised graph representation learning by leveraging a contrastive objective at the node level. Specifically, we generate two graph views by corruption and learn node representations by maximizing the agreement of node representations in these two views. To provide diverse node contexts for the contrastive objective, we propose a hybrid scheme for generating graph views on both structure and attribute levels. Besides, we provide theoretical justification behind our motivation from two perspectives, mutual information and the classical triplet loss. We perform empirical experiments on both transductive and inductive learning tasks using a variety of real-world datasets. Experimental experiments demonstrate that despite its simplicity, our proposed method consistently outperforms existing state-of-the-art methods by large margins. Moreover, our unsupervised method even surpasses its supervised counterparts on transductive tasks, demonstrating its great potential in real-world applications.