Stability and Generalization of Hypergraph Collaborative Networks

Michael K. Ng, Hanrui Wu, Andy Yip*

*Corresponding author for this work

Research output: Contribution to journalJournal articlepeer-review

2 Citations (Scopus)

Abstract

Graph neural networks have been shown to be very effective in utilizing pairwise relationships across samples. Recently, there have been several successful proposals to generalize graph neural networks to hypergraph neural networks to exploit more complex relationships. In particular, the hypergraph collaborative networks yield superior results compared to other hypergraph neural networks for various semi-supervised learning tasks. The collaborative network can provide high quality vertex embeddings and hyperedge embeddings together by formulating them as a joint optimization problem and by using their consistency in reconstructing the given hypergraph. In this paper, we aim to establish the algorithmic stability of the core layer of the collaborative network and provide generalization guarantees. The analysis sheds light on the design of hypergraph filters in collaborative networks, for instance, how the data and hypergraph filters should be scaled to achieve uniform stability of the learning process. Some experimental results on real-world datasets are presented to illustrate the theory.

Original languageEnglish
Pages (from-to)184-196
Number of pages13
JournalMachine Intelligence Research
Volume21
Issue number1
Early online date15 Jan 2024
DOIs
Publication statusPublished - Feb 2024

Scopus Subject Areas

  • Control and Systems Engineering
  • Signal Processing
  • Modelling and Simulation
  • Computer Vision and Pattern Recognition
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence
  • Applied Mathematics

User-Defined Keywords

  • collaborative networks
  • generalization guarantees
  • graph convolutional neural networks (CNNs)
  • hyperedges
  • Hypergraphs
  • stability
  • vertices

Fingerprint

Dive into the research topics of 'Stability and Generalization of Hypergraph Collaborative Networks'. Together they form a unique fingerprint.

Cite this