Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
SINO: Scale-Invariant Neural Operator
Kaichen Ouyang, Chenglei Yu, Chuanrui Wang +1
In scientific machine learning, physical fields governed by partial differential equations exhibit low-rank structure and scale invariance. When solving equations on coarse grids,…
cs.LG2025
Rethinking Over-Smoothing in Graph Neural Networks: A Perspective from Anderson Localization
Kaichen Ouyang
Graph Neural Networks (GNNs) have shown great potential in graph data analysis due to their powerful representation capabilities. However, as the network depth increases, the issue…