Kernelized Hypergraph Neural Networks

Yifan Feng, Yifan Zhang, Shihui Ying, Shaoyi Du, Yue Gao

Abstract

Hypergraph Neural Networks (HGNNs) have attracted much attention for high-order structural data learning. Existing methods mainly focus on simple mean-based aggregation or manually combining multiple aggregations to capture multiple information on hypergraphs. However, those methods inherently lack continuous non-linear modeling ability and are sensitive to varied distributions. Although some kernel-based aggregations on GNNs and CNNs can capture non-linear patterns to some degree, those methods are restricted in the low-order correlation and may cause unstable computation in training. In this work, we introduce Kernelized Hypergraph Neural Networks (KHGNN) and its variant, Half-Kernelized Hypergraph Neural Networks (H-KHGNN), which synergize mean-based and max-based aggregation functions to enhance representation learning on hypergraphs. KHGNN’s kernelized aggregation strategy adaptively captures both semantic and structural information via learnable parameters, offering a mathematically grounded blend of kernelized aggregation approaches for comprehensive feature extraction. H-KHGNN addresses the challenge of overfitting in less intricate hypergraphs by employing non-linear aggregation selectively in the vertex-to-hyperedge message-passing process, thus reducing model complexity. Our theoretical contributions reveal a bounded gradient for kernelized aggregation, ensuring stability during training and inference. Empirical results demonstrate that KHGNN and H-KHGNN outperform state-of-the-art models across 10 graph/hypergraph datasets, with ablation studies demonstrating the effectiveness and computational stability of our method.
BibTeX
@article{feng2025kernelized,
  author = {Yifan Feng and Yifan Zhang and Shihui Ying and Shaoyi Du and Yue Gao},
  title = {{Kernelized Hypergraph Neural Networks}},
  journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
  year = {2025},
  url = {https://openreview.net/forum?id=MydQmUtrtN},
}

Loading related content...

Figure