• myGriffith
    • Staff portal
    • Contact Us⌄
      • Future student enquiries 1800 677 728
      • Current student enquiries 1800 154 055
      • International enquiries +61 7 3735 6425
      • General enquiries 07 3735 7111
      • Online enquiries
      • Staff phonebook
    View Item 
    •   Home
    • Griffith Research Online
    • Conference outputs
    • View Item
    • Home
    • Griffith Research Online
    • Conference outputs
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Browse

  • All of Griffith Research Online
    • Communities & Collections
    • Authors
    • By Issue Date
    • Titles
  • This Collection
    • Authors
    • By Issue Date
    • Titles
  • Statistics

  • Most Popular Items
  • Statistics by Country
  • Most Popular Authors
  • Support

  • Contact us
  • FAQs
  • Admin login

  • Login
  • Heterogeneous Hypergraph Embedding for Graph Classification

    Thumbnail
    View/Open
    Nguyen460827-Accepted.pdf (2.147Mb)
    File version
    Accepted Manuscript (AM)
    Author(s)
    Sun, Xiangguo
    Yin, Hongzhi
    Liu, Bo
    Chen, Hongxu
    Cao, Jiuxin
    Shao, Yingxia
    Viet Hung, Nguyen Quoc
    Griffith University Author(s)
    Nguyen, Henry
    Year published
    2021
    Metadata
    Show full item record
    Abstract
    Recently, graph neural networks have been widely used for network embedding because of their prominent performance in pairwise relationship learning. In the real world, a more natural and common situation is the coexistence of pairwise relationships and complex non-pairwise relationships, which is, however, rarely studied. In light of this, we propose a graph neural network-based representation learning framework for heterogeneous hypergraphs, an extension of conventional graphs, which can well characterize multiple non-pairwise relations. Our framework first projects the heterogeneous hypergraph into a series of snapshots ...
    View more >
    Recently, graph neural networks have been widely used for network embedding because of their prominent performance in pairwise relationship learning. In the real world, a more natural and common situation is the coexistence of pairwise relationships and complex non-pairwise relationships, which is, however, rarely studied. In light of this, we propose a graph neural network-based representation learning framework for heterogeneous hypergraphs, an extension of conventional graphs, which can well characterize multiple non-pairwise relations. Our framework first projects the heterogeneous hypergraph into a series of snapshots and then we take the Wavelet basis to perform localized hypergraph convolution. Since the Wavelet basis is usually much sparser than the Fourier basis, we develop an efficient polynomial approximation to the basis to replace the time-consuming Laplacian decomposition. Extensive evaluations have been conducted and the experimental results show the superiority of our method. In addition to the standard tasks of network embedding evaluation such as node classification, we also apply our method to the task of spammers detection and the superior performance of our framework shows that relationships beyond pairwise are also advantageous in the spammer detection. To make our experiment repeatable, source codes and related datasets are available at https://xiangguosun.mystrikingly.com
    View less >
    Conference Title
    Proceedings of the 14th ACM International Conference on Web Search and Data Mining
    DOI
    https://doi.org/10.1145/3437963.3441835
    Copyright Statement
    © ACM, 2021. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in WSDM '21: Proceedings of the 14th ACM International Conference on Web Search and Data Mining, ISBN: 978-1-4503-8297-7, https://doi.org/10.1145/3437963.3441835
    Subject
    Artificial Intelligence and Image Processing
    cs.SI
    Publication URI
    http://hdl.handle.net/10072/403224
    Collection
    • Conference outputs

    Footer

    Disclaimer

    • Privacy policy
    • Copyright matters
    • CRICOS Provider - 00233E

    Tagline

    • Gold Coast
    • Logan
    • Brisbane - Queensland, Australia
    First Peoples of Australia
    • Aboriginal
    • Torres Strait Islander