AINeutralarXiv – CS AI · Jun 196/10
🧠
Boundary Embedding Shaping with Adaptive Contrastive Learning for Graph Structural Disentanglement
Researchers propose Boundary Embedding Shaping (BES), a new machine learning technique that improves graph neural networks by addressing structural noise at decision boundaries. The method uses adaptive contrastive learning to enhance node classification accuracy by up to 5%, offering a lightweight plug-in solution for existing GNN models.