Explicit Feature Interaction-aware Graph Neural Networks
Autor: | Kim, Minkyu, Choi, Hyun-Soo, Kim, Jinho |
---|---|
Rok vydání: | 2022 |
Předmět: | |
Zdroj: | IEEE Access, vol. 12, pp. 15438-15446, Jan. 2024 |
Druh dokumentu: | Working Paper |
DOI: | 10.1109/ACCESS.2024.3357887 |
Popis: | 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 Comment: 10 pages, 9 figures, 4 tables |
Databáze: | arXiv |
Externí odkaz: |