Dual Feature Interaction-Based Graph Convolutional Network

Zhongying Zhao, Zhan Yang, Chao Li, Qingtian Zeng, Weili Guan, Mengchu Zhou

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

Graphs are widely used to model various practical applications. In recent years, graph convolution networks (GCNs) have attracted increasing attention due to the extension of convolution operation from traditional grid data to graph one. However, the representation ability of current GCNs is undoubtedly limited because existing work fails to consider feature interactions. Toward this end, we propose a Dual Feature Interaction-based GCN. Specifically, it models feature interaction in the aspects of 1) node features where we use Newton&#x0027;s identity to extract different-order cross features implicit in the original features and design an attention mechanism to fuse them; and 2) graph convolution where we capture the pairwise interactions among nodes in the neighborhood to expand a weighted sum operation. We evaluate the proposed model with graph data from different fields, and the experimental results on semi-supervised node classification and link prediction demonstrate the effectiveness of the proposed GCN. The data and source codes of this work are available at <uri>https://github.com/ZZY-GraphMiningLab/DFI-GCN</uri>.

Original languageEnglish (US)
Pages (from-to)1-12
Number of pages12
JournalIEEE Transactions on Knowledge and Data Engineering
DOIs
StateAccepted/In press - 2022

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Computer Science Applications
  • Computational Theory and Mathematics

Keywords

  • Convolution
  • Deep learning
  • Feature extraction
  • Feature interaction
  • Frequency modulation
  • Neural networks
  • Predictive models
  • Task analysis
  • graph convolutional network
  • graph neural network
  • network embedding

Fingerprint

Dive into the research topics of 'Dual Feature Interaction-Based Graph Convolutional Network'. Together they form a unique fingerprint.

Cite this