Viet-Anh on Software Logo

What is: Graph Contrastive Coding?

SourceGCC: Graph Contrastive Coding for Graph Neural Network Pre-Training
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

Graph Contrastive Coding is a self-supervised graph neural network pre-training framework to capture the universal network topological properties across multiple networks. GCC's pre-training task is designed as subgraph instance discrimination in and across networks and leverages contrastive learning to empower graph neural networks to learn the intrinsic and transferable structural representations.