2025 Poster "oversmoothing problem" Papers
2 papers found
Deeper with Riemannian Geometry: Overcoming Oversmoothing and Oversquashing for Graph Foundation Models
Li Sun, Zhenhao Huang, Ming Zhang et al.
NeurIPS 2025posterarXiv:2510.17457
1
citations
Residual Connections and Normalization Can Provably Prevent Oversmoothing in GNNs
Michael Scholkemper, Xinyi Wu, Ali Jadbabaie et al.
ICLR 2025posterarXiv:2406.02997
22
citations