Multi-view heterogeneous graph learning with compressed hypergraph neural networks.

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

Abstract

Multi-view learning is an emerging field of multi-modal fusion, which involves representing a single instance using multiple heterogeneous features to improve compatibility prediction. However, existing graph-based multi-view learning approaches are implemented on homogeneous assumptions and pairwise relationships, which may not adequately capture the complex interactions among real-world instances. In this paper, we design a compressed hypergraph neural network from the perspective of multi-view heterogeneous graph learning. This approach effectively captures rich multi-view heterogeneous semantic information, incorporating a hypergraph structure that simultaneously enables the exploration of higher-order correlations between samples in multi-view scenarios. Specifically, we introduce efficient hypergraph convolutional networks based on an explainable regularizer-centered optimization framework. Additionally, a low-rank approximation is adopted as hypergraphs to reformat the initial complex multi-view heterogeneous graph. Extensive experiments compared with several advanced node classification methods and multi-view classification methods have demonstrated the feasibility and effectiveness of the proposed method.

Authors

  • Aiping Huang
    School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, 611731, China. Electronic address: sxxhap@163.com.
  • Zihan Fang
    College of Computer and Data Science, Fuzhou University, Fuzhou 350116, China. Electronic address: fzihan11@163.com.
  • Zhihao Wu
    VoxelCloud, Inc., United States.
  • Yanchao Tan
    College of Computer and Data Science, Fuzhou University, Fuzhou, China.
  • Peng Han
    Lars Bolund Institute of Regenerative Medicine, Qingdao-Europe Advanced Institute for Life Sciences, BGI-Qingdao, Qingdao, China.
  • Shiping Wang
    College of Computer and Data Science, Fuzhou University, Fuzhou 350116, China; Guangdong Provincial Key Laboratory of Big Data Computing, The Chinese University of Hong Kong, Shenzhen 518172, China. Electronic address: shipingwangphd@163.com.
  • Le Zhang
    State Key Laboratory of Multiphase Complex Systems, Institute of Process Engineering, Chinese Academy of Sciences, Beijing 100190, China; College of Chemical Engineering, University of Chinese Academy of Sciences, Beijing 100049, China; Key Laboratory of Science and Technology on Particle Materials, Institute of Process Engineering, Chinese Academy of Sciences, Beijing 361021, China.