Explicit Feature Interaction-aware Graph Neural Networks
This addresses a limitation in GNN design for graph learning tasks, though it appears incremental as it builds on existing GNN methods.
The paper tackles the problem of GNNs overlooking low-order feature interactions in graph-structured data by introducing EFI-GNN, a multilayer linear network that explicitly models arbitrary-order feature interactions, resulting in competitive performance and improved predictive performance when jointly trained with existing GNNs.
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