Graph Contrastive Coding

2000년 도입 · 논문 4편에서 사용

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.

출처: GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training

소개 논문: GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training