5 papers
Towards Trustworthy Hypergraph Neural Networks under Label Noise
Mengyao Zhou, Zhiheng Zhou, Xiao Han +1
Hypergraph neural networks (HGNNs) have demonstrated remarkable capabilities in processing complex higher-order relationships. However, their performance is highly dependent on lab…
From Diffusion to Reaction-Diffusion: A Dynamical-Systems View of Oversmoothing in Hypergraph Neural Networks
Zhiheng Zhou, Mengyao Zhou, Yancheng Chen +3
Higher-order couplings enhance the expressive power of hypergraph neural networks (HGNNs), but they also intensify representation collapse in deep propagation due to strong multi-w…
Hypergraph Neural Stochastic Diffusion: An SDE Framework for Uncertainty Estimation
Zhiheng Zhou, Mengyao Zhou, Dengyi Zhao +2
Hypergraph neural networks have shown powerful capability in modeling higher-order relations, yet their predictive uncertainty remains underexplored. Unlike pairwise graphs, uncert…
Hypergraph Neural Diffusion: A PDE-Inspired Framework for Hypergraph Message Passing
Zhiheng Zhou, Mengyao Zhou, Xixun Lin +2
Hypergraph neural networks (HGNNs) have shown remarkable potential in modeling high-order relationships that naturally arise in many real-world data domains. However, existing HGNN…
Tackling Over-smoothing on Hypergraphs: A Ricci Flow-guided Neural Diffusion Approach
Mengyao Zhou, Zhiheng Zhou, Xiao Han +3
Hypergraph neural networks (HGNNs) have demonstrated strong capabilities in modeling complex higher-order relationships. However, existing HGNNs often suffer from over-smoothing as…