Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Deep Graph Contrastive Representation Learning

About

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.

Yanqiao Zhu, Yichen Xu, Feng Yu, Qiang Liu, Shu Wu, Liang Wang• 2020

Related benchmarks

TaskDatasetResultRank
Node ClassificationCora
Accuracy84.79
885
Node ClassificationCiteseer
Accuracy71.7
804
Node ClassificationPubmed
Accuracy87.04
742
Node ClassificationCiteseer (test)
Accuracy0.712
729
Node ClassificationCora (test)
Mean Accuracy77.1
687
Node ClassificationChameleon
Accuracy68.25
549
Node ClassificationSquirrel
Accuracy53.15
500
Node ClassificationPubMed (test)
Accuracy79.5
500
Node Classificationogbn-arxiv (test)
Accuracy65.1
382
Node ClassificationPubmed
Accuracy80.6
307
Showing 10 of 109 rows
...

Other info

Code

Follow for update