Explicit Feature Interaction-Aware Graph Neural Network
IEEE Access · 2024 · 12 · 15438-15446
DOI: 10.1109/access.2024.3357887 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2024. Verfasst von Minkyu Kim und 2 weiteren Autor:innen. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Research Foundation of Korea (NRF) Grant, Korean Government.
Abstract (Originalsprache)
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.
Förderung
- National Research Foundation of Korea (NRF) Grant
- Korean Government
Zitieren
APA
Kim, M., Choi, H., & Kim, J. (2024). Explicit Feature Interaction-Aware Graph Neural Network. IEEE Access, 12, 15438-15446. https://doi.org/10.1109/access.2024.3357887
Vancouver
Kim M, Choi H, Kim J. Explicit Feature Interaction-Aware Graph Neural Network. IEEE Access. 2024;12:15438-15446. doi:10.1109/access.2024.3357887
BibTeX
@article{Kim2024,
author = {Kim, Minkyu and Choi, Hyun-Soo and Kim, Jinho},
title = {Explicit Feature Interaction-Aware Graph Neural Network},
journal = {IEEE Access},
year = {2024},
volume = {12},
pages = {15438--15446},
doi = {10.1109/access.2024.3357887}
}
EUVIMED