AINeutralarXiv – CS AI · 7h ago6/10
🧠
Graph is a Natural Regularization: Revisiting Vector Quantization for Graph Representation Learning
Researchers propose RGVQ, a novel framework addressing codebook collapse in Vector Quantization for graph neural networks, a technical limitation that degrades token expressiveness and generalization. By integrating graph topology as regularization and introducing soft assignments, RGVQ improves codebook utilization across downstream graph learning tasks.