Explicit Feature Interaction-aware Graph Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kim, Minkyu, Choi, Hyun-Soo, Kim, Jinho
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909222570033152
author Kim, Minkyu
Choi, Hyun-Soo
Kim, Jinho
author_facet Kim, Minkyu
Choi, Hyun-Soo
Kim, Jinho
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2204_03225
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Explicit Feature Interaction-aware Graph Neural Networks
Kim, Minkyu
Choi, Hyun-Soo
Kim, Jinho
Machine Learning
Artificial Intelligence
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
title Explicit Feature Interaction-aware Graph Neural Networks
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2204.03225