Yifan Feng

Generating Hypergraph-Based High-Order Representations of Whole-Slide Histopathological Images for Survival Prediction

2022 · IEEE Transactions on Pattern Analysis and Machine Intelligence

Patient survival prediction based on gigapixel whole-slide histopathological images (WSIs) has become increasingly prevalent in recent years. A key challenge of this task is achieving an informative survival-specific global representation from those WSIs with highly …

LightHGNN: Distilling Hypergraph Neural Networks into MLPs for $100\times$ Faster Inference

2024 · arXiv (Cornell University)

Hypergraph Neural Networks (HGNNs) have recently attracted much attention and exhibited satisfactory performance due to their superiority in high-order correlation modeling. However, it is noticed that the high-order modeling capability of hypergraph also brings increased …

Hypergraph Foundation Model

2025 · IEEE Transactions on Pattern Analysis and Machine Intelligence

Hypergraph neural networks (HGNNs) effectively model complex high-order relationships in domains like protein interactions and social networks by connecting multiple vertices through hyperedges, enhancing modeling capabilities, and reducing information loss. Developing foundation models for hypergraphs …