AI RESEARCH
Tackling Over-smoothing on Hypergraphs: A Ricci Flow-guided Neural Diffusion Approach
arXiv CS.AI
•
ArXi:2603.15696v1 Announce Type: cross Hypergraph neural networks (HGNNs) have nstrated strong capabilities in modeling complex higher-order relationships. However, existing HGNNs often suffer from over-smoothing as the number of layers increases and lack effective control over message passing among nodes. Inspired by the theory of Ricci flow in differential geometry, we theoretically establish that