Yongchun Gu — accepted AI-conference papers

2025

Deep Hypergraph Neural Networks with Tight Framelets

Ming Li, Yujie Fang, Yi Wang, Han Feng, Yongchun Gu, Lu Bai +1

AAAI 2025technical

Hypergraphs provide a flexible framework for modeling high-order (complex) interactions among multiple entities, extending beyond traditional pairwise correlations in graph structures. However, deep hypergraph neural networks (HGNNs) often face the challenge of oversmoothing with increasing depth, s…

Cited by 1 Source ↗PDF ↗Scholar ↗

2025

When Hypergraph Meets Heterophily: New Benchmark Datasets and Baseline

Ming Li, Yongchun Gu, Yi Wang, Yujie Fang, Lu Bai, Xiaosheng Zhuang +1

AAAI 2025technical

Hypergraph neural networks (HNNs) have shown promise in handling tasks characterized by high-order correlations, achieving notable success across various applications. However, there has been limited focus on heterophilic hypergraph learning (HHL), in contrast to the increasing attention given to gr…

Cited by 1 Source ↗PDF ↗Scholar ↗