GraphCL: Contrastive Self-Supervised Learning of Graph Representations

07/15/2020
by   Hakim Hafidi, et al.
56

We propose Graph Contrastive Learning (GraphCL), a general framework for learning node representations in a self supervised manner. GraphCL learns node embeddings by maximizing the similarity between the representations of two randomly perturbed versions of the intrinsic features and link structure of the same node's local subgraph. We use graph neural networks to produce two representations of the same node and leverage a contrastive learning loss to maximize agreement between them. In both transductive and inductive learning setups, we demonstrate that our approach significantly outperforms the state-of-the-art in unsupervised learning on a number of node classification benchmarks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/11/2023

Contrastive Learning under Heterophily

Graph Neural Networks are powerful tools for learning node representatio...
research
02/07/2022

Graph Self-supervised Learning with Accurate Discrepancy Learning

Self-supervised learning of graph neural networks (GNNs) aims to learn a...
research
05/01/2023

A Simplified Framework for Contrastive Learning for Node Representations

Contrastive learning has recently established itself as a powerful self-...
research
03/15/2022

Supervised Contrastive Learning with Structure Inference for Graph Classification

Advanced graph neural networks have shown great potentials in graph clas...
research
05/30/2023

A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks

While contrastive self-supervised learning has become the de-facto learn...
research
06/23/2020

Gaining insight into SARS-CoV-2 infection and COVID-19 severity using self-supervised edge features and Graph Neural Networks

Graph Neural Networks (GNN) have been extensively used to extract meanin...
research
11/19/2019

GraphTER: Unsupervised Learning of Graph Transformation Equivariant Representations via Auto-Encoding Node-wise Transformations

Recent advances in Graph Convolutional Neural Networks (GCNNs) have show...

Please sign up or login with your details

Forgot password? Click here to reset