Description
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.
Papers Using This Method
Joyful: Joint Modality Fusion and Graph Contrastive Learning for Multimodal Emotion Recognition2023-11-18Successive POI Recommendation via Brain-inspired Spatiotemporal Aware Representation2021-09-29Graph Contrastive Learning for Anomaly Detection2021-08-17GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training2020-06-17