Dual Feature Interaction-Based Graph Convolutional Network

Document Type

Article

Publication Date

9-1-2023

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'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.

Identifier

85141576299 (Scopus)

Publication Title

IEEE Transactions on Knowledge and Data Engineering

External Full Text Location

https://doi.org/10.1109/TKDE.2022.3220789

e-ISSN

15582191

ISSN

10414347

First Page

9019

Last Page

9030

Issue

9

Volume

35

Grant

CICIP2020001

Fund Ref

National Natural Science Foundation of China

This document is currently not available here.

Share

COinS