Dual Feature Interaction-Based Graph Convolutional Network
- 9 November 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 35 (9) , 9019-9030
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. The data and source codes of this work are available at https://github.com/ZZY-GraphMiningLab/DFI-GCN .Keywords
Funding Information
- National Natural Science Foundation of China (62072288, 61702306, 61433012)
- Taishan Scholar Program of Shandong Province
- Natural Science Foundation of Shandong Province (ZR2018BF013, ZR2022MF268)
- Open Project Foundation of Intelligent Information Processing Key Laboratory of Shanxi Province (CICIP2020001)
This publication has 36 references indexed in Scilit:
- Deep & Cross Network for Ad Click Predictions2017
- DeepFM: A Factorization-Machine based Neural Network for CTR Prediction2017
- DeepWalk2014
- Leveraging social media networks for classificationData Mining and Knowledge Discovery, 2011
- Link Prediction via Matrix Factorization2011
- Collective Classification in Network DataAI Magazine, 2008
- Supervised enzyme network inference from the integration of genomic data and chemical informationBioinformatics, 2005
- Learning kernels from biological networks by maximizing entropyBioinformatics, 2004
- The MID3 Data Set, 1993—2001: Procedures, Coding Rules, and DescriptionConflict Management and Peace Science, 2004
- Backpropagation Applied to Handwritten Zip Code RecognitionNeural Computation, 1989