Graph Contrastive Learning with Augmentations

10/22/2020
by   Yuning You, et al.
13

Generalizable, transferrable, and robust representation learning on graph-structured data remains a challenge for current graph neural networks (GNNs). Unlike what has been developed for convolutional neural networks (CNNs) for image data, self-supervised learning and pre-training are less explored for GNNs. In this paper, we propose a graph contrastive learning (GraphCL) framework for learning unsupervised representations of graph data. We first design four types of graph augmentations to incorporate various priors. We then systematically study the impact of various combinations of graph augmentations on multiple datasets, in four different settings: semi-supervised, unsupervised, and transfer learning as well as adversarial attacks. The results show that, even without tuning augmentation extents nor using sophisticated GNN architectures, our GraphCL framework can produce graph representations of similar or better generalizability, transferrability, and robustness compared to state-of-the-art methods. We also investigate the impact of parameterized graph augmentation extents and patterns, and observe further performance gains in preliminary experiments. Our codes are available at https://github.com/Shen-Lab/GraphCL.

READ FULL TEXT
research
03/27/2021

Self-supervised Graph Neural Networks without explicit negative sampling

Real world data is mostly unlabeled or only few instances are labeled. M...
research
06/10/2021

Adversarial Graph Augmentation to Improve Graph Contrastive Learning

Self-supervised learning of graph neural networks (GNN) is in great need...
research
11/05/2021

Collaborative Graph Contrastive Learning: Data Augmentation Composition May Not be Necessary for Graph Representation Learning

Unsupervised graph representation learning is a non-trivial topic for gr...
research
05/25/2021

Graph Self Supervised Learning: the BT, the HSIC, and the VICReg

Self-supervised learning and pre-training strategies have developed over...
research
01/14/2022

Training Free Graph Neural Networks for Graph Matching

We present TFGM (Training Free Graph Matching), a framework to boost the...
research
11/10/2020

Self-supervised Graph Representation Learning via Bootstrapping

Graph neural networks (GNNs) apply deep learning techniques to graph-str...
research
05/04/2023

Revisiting Graph Contrastive Learning for Anomaly Detection

Combining Graph neural networks (GNNs) with contrastive learning for ano...

Please sign up or login with your details

Forgot password? Click here to reset