Share your thoughts, 1 month free Claude Pro on usSee more
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
Graph ClassificationPROTEINS
Accuracy75.4
1383
Graph ClassificationMUTAG
Accuracy89
1229
Node ClassificationCora
Accuracy84.79
1225
Node ClassificationCiteseer
Accuracy71.72
1037
Node ClassificationCiteseer (test)
Accuracy0.7379
1013
Node ClassificationCora (test)
Mean Accuracy88.56
951
Node ClassificationChameleon
Accuracy68.25
936
Node ClassificationPubmed
Accuracy87.04
902
Node ClassificationCornell
Accuracy42.7
900
Node ClassificationWisconsin
Accuracy58.04
898
Showing 10 of 223 rows
...

Other info

Code

Follow for update