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

Graph Contrastive Learning with Adaptive Augmentation

About

Recently, contrastive learning (CL) has emerged as a successful method for unsupervised graph representation learning. Most graph CL methods first perform stochastic augmentation on the input graph to obtain two graph views and maximize the agreement of representations in the two views. Despite the prosperous development of graph CL methods, the design of graph augmentation schemes -- a crucial component in CL -- remains rarely explored. We argue that the data augmentation schemes should preserve intrinsic structures and attributes of graphs, which will force the model to learn representations that are insensitive to perturbation on unimportant nodes and edges. However, most existing methods adopt uniform data augmentation schemes, like uniformly dropping edges and uniformly shuffling features, leading to suboptimal performance. In this paper, we propose a novel graph contrastive representation learning method with adaptive augmentation that incorporates various priors for topological and semantic aspects of the graph. Specifically, on the topology level, we design augmentation schemes based on node centrality measures to highlight important connective structures. On the node attribute level, we corrupt node features by adding more noise to unimportant node features, to enforce the model to recognize underlying semantic information. We perform extensive experiments of node classification on a variety of real-world datasets. Experimental results demonstrate that our proposed method consistently outperforms existing state-of-the-art baselines and even surpasses some supervised counterparts, which validates the effectiveness of the proposed contrastive framework with adaptive augmentation.

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

Related benchmarks

TaskDatasetResultRank
Node ClassificationCora
Accuracy83.43
885
Node ClassificationCiteseer
Accuracy68.2
804
Node ClassificationPubmed
Accuracy85.65
742
Node ClassificationPubmed
Accuracy81
307
Node ClassificationwikiCS
Accuracy78.3
198
Node ClassificationPhoto
Mean Accuracy92.5
165
Node ClassificationPhysics
Accuracy95.7
145
Node ClassificationComputers
Mean Accuracy74.87
143
Node ClassificationCS
Accuracy93.1
128
Molecular property predictionMoleculeNet BBBP (scaffold)
ROC AUC71.2
117
Showing 10 of 42 rows

Other info

Follow for update