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
Recommended Citation
Zhao, Zhongying; Yang, Zhan; Li, Chao; Zeng, Qingtian; Guan, Weili; and Zhou, Meng Chu, "Dual Feature Interaction-Based Graph Convolutional Network" (2023). Faculty Publications. 1489.
https://digitalcommons.njit.edu/fac_pubs/1489