Stability-Shaped Deep Graph Learning
In deep graph neural networks, increasing depth enlarges the receptive field but often leads to over-smoothing, where node representations tend to align. We develop a unified, mode-wise stability framework for deep GNN propagation that provides a principled characterization of over-smoothing. By interpreting layer dept...
Jun-You Zhu, Lang-Zhou He, Fen-Ying Cai et al.
· 0 citations