Timezone: »

 
Poster
Adversarial Graph Augmentation to Improve Graph Contrastive Learning
Susheel Suresh · Pan Li · Cong Hao · Jennifer Neville

Tue Dec 07 08:30 AM -- 10:00 AM (PST) @
in Poster Session 1 »

Self-supervised learning of graph neural networks (GNN) is in great need because of the widespread label scarcity issue in real-world graph/network data. Graph contrastive learning (GCL), by training GNNs to maximize the correspondence between the representations of the same graph in its different augmented forms, may yield robust and transferable GNNs even without using labels. However, GNNs trained by traditional GCL often risk capturing redundant graph features and thus may be brittle and provide sub-par performance in downstream tasks. Here, we propose a novel principle, termed adversarial-GCL (\textit{AD-GCL}), which enables GNNs to avoid capturing redundant information during the training by optimizing adversarial graph augmentation strategies used in GCL. We pair AD-GCL with theoretical explanations and design a practical instantiation based on trainable edge-dropping graph augmentation. We experimentally validate AD-GCL by comparing with the state-of-the-art GCL methods and achieve performance gains of up-to~14\% in unsupervised, ~6\% in transfer and~3\% in semi-supervised learning settings overall with 18 different benchmark datasets for the tasks of molecule property regression and classification, and social network classification.

Keywords: Deep Learning · Machine Learning · Self-Supervised Learning · Graph Learning · Contrastive Learning · Representation Learning · Semi-Supervised Learning

Author Information

Susheel Suresh (Purdue University)
Pan Li (Stanford University)
Cong Hao (Georgia Institute of Technology)
Jennifer Neville (Purdue University)

More from the Same Authors