Explicit Feature Interaction-aware Graph Neural Networks

TL;DR

EFI-GNN is a novel graph neural network that explicitly models arbitrary-order feature interactions, improving interpretability and performance when combined with traditional GNNs.

Contribution

This paper introduces EFI-GNN, a linear multilayer network that explicitly captures all feature interactions in graphs, addressing limitations of conventional GNNs.

Findings

EFI-GNN achieves competitive performance with existing GNNs.

Joint training of EFI-GNN with GNN improves predictive accuracy.

EFI-GNN provides interpretable predictions due to its linear structure.

Abstract

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