Revisiting Positive Samples in Graph Contrastive Learning: From the Perspective of Message Passing
Researchers have developed a new method called SPGCL to improve Graph Contrastive Learning (GCL). They found that existing GCL methods often fail to effectively learn from positive samples due to the message-passing mechanism in graph encoders. SPGCL aims to fix this by selectively propagating high-energy features and using low-energy features for more reliable positive sampling, leading to better performance in experiments. AI
IMPACT Enhances graph representation learning, potentially improving downstream AI tasks that rely on graph data.