Explicit Feature Interaction-Aware Graph Neural Network

Graph neural networks (GNNs) are powerful tools for handling graph-structured data. However, their design often limits them to learning only higher-order feature interactions, leaving low-order feature interactions overlooked. To address this problem, we introduce a novel GNN method called explicit...

Full description

Saved in:
Bibliographic Details
Published inIEEE access Vol. 12; pp. 15438 - 15446
Main Authors Kim, Minkyu, Choi, Hyun-Soo, Kim, Jinho
Format Journal Article
LanguageEnglish
Published Piscataway IEEE 2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Aggregates
Artificial intelligence
Deep learning
feature interactions
Graph neural networks
interpretable AI
Multilayers
Nonhomogeneous media
Performance prediction
Recurrent neural networks
Source code
Structured data
Task analysis
Training
Online AccessGet full text

Cover

More Information
Summary:Graph neural networks (GNNs) are powerful tools for handling graph-structured data. However, their design often limits them to learning only higher-order feature interactions, leaving low-order feature interactions overlooked. To address this problem, we introduce a novel GNN method called explicit feature interaction-aware graph neural network (EFI-GNN). Unlike conventional GNNs, EFI-GNN is a multilayer linear network designed to model arbitrary-order feature interactions explicitly within graphs. To validate the efficacy of EFI-GNN, we conduct experiments using various datasets. The experimental results demonstrate that EFI-GNN has competitive performance with existing GNNs, and when a GNN is jointly trained with EFI-GNN, predictive performance sees an improvement. Furthermore, the predictions made by EFI-GNN are interpretable, owing to its linear construction. The source code of EFI-GNN is available at https://github.com/gim4855744/EFI-GNN .
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2024.3357887