IHGNN: Iterative Interpretable HyperGraph Neural Network for semi-supervised classification.

Journal: Neural networks : the official journal of the International Neural Network Society
Published Date:

Abstract

Learning on hypergraphs has garnered significant attention recently due to their ability to effectively represent complex higher-order interactions among multiple entities compared to conventional graphs. Nevertheless, the majority of existing methods are direct extensions of graph neural networks, and they exhibit noteworthy limitations. Specifically, most of these approaches primarily rely on either the Laplacian matrix with information distortion or heuristic message passing techniques. The former tends to escalate algorithmic complexity, while the latter lacks a solid theoretical foundation. To address these limitations, we propose a novel hypergraph neural network named IHGNN, which is grounded in an energy minimization function formulated for hypergraphs. Our analysis reveals that propagation layers align well with the message-passing paradigm in the context of hypergraphs. IHGNN achieves a favorable trade-off between performance and interpretability. Furthermore, it effectively balances the significance of node features and hypergraph topology across a diverse range of datasets. We conducted extensive experiments on 15 datasets, and the results highlight the superior performance of IHGNN in the task of hypergraph node classification across nearly all benchmarking datasets.

Authors

  • Hongwei Zhang
    Jiangsu Provincial Key Laboratory for TCM Evaluation and Translational Development, China Pharmaceutical University, Nanjing, Jiangsu 211198, China.
  • Saizhuo Wang
    The Hong Kong University of Science and Technology, Hong Kong Special Administrative Region of China, China. Electronic address: swangeh@connect.ust.hk.
  • Zixin Hu
    State Key Laboratory of Genetic Engineering and Innovation Center of Genetics and Development, School of Life Sciences, Fudan University, Shanghai, China.
  • Yuan Qi
    Fudan University, Shanghai, China. Electronic address: qiyuan@fudan.edu.cn.
  • Zengfeng Huang
    Fudan University, Shanghai, China. Electronic address: huangzf@fudan.edu.cn.
  • Jian Guo
    Department of Radiology, Beijing Tongren Hospital, Capital Medical University, No. 1 Dongjiaominxiang Street, Dongcheng District, Beijing, 100730, China; Clinical Center for Eye Tumors, Capital Medical University, Beijing, 100730, China.