Saved in:
Bibliographic Details
Main Authors: Zhang, Aihu, Xu, Jiaxing, Lan, Mengcheng, Xiang, Shili, Ke, Yiping
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.22362
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908760815960064
author Zhang, Aihu
Xu, Jiaxing
Lan, Mengcheng
Xiang, Shili
Ke, Yiping
author_facet Zhang, Aihu
Xu, Jiaxing
Lan, Mengcheng
Xiang, Shili
Ke, Yiping
contents Graph Neural Networks (GNNs) have achieved significant success in various learning tasks on graph-structured data. Nevertheless, most GNNs struggle to generalize to heterophilic neighborhoods. Additionally, many GNNs ignore the directional nature of real-world graphs, resulting in suboptimal performance on directed graphs with asymmetric structures. In this work, we propose Directed Homophily-aware Graph Neural Network (DHGNN), a novel framework that addresses these limitations by incorporating homophily-aware and direction-sensitive components. DHGNN employs a resettable gating mechanism to adaptively modulate message contributions based on homophily levels and informativeness, and a structure-aware noise-tolerant fusion module to effectively integrate node representations from the original and reverse directions. Extensive experiments on both homophilic and heterophilic directed graph datasets demonstrate that DHGNN outperforms state-of-the-art methods in node classification and link prediction. In particular, DHGNN improves over the best baseline by up to 15.07\% in link prediction. Our analysis further shows that the gating mechanism captures directional homophily gaps and fluctuating homophily across layers, providing deeper insights into message-passing behavior on complex graph structures.
format Preprint
id arxiv_https___arxiv_org_abs_2505_22362
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Directed Homophily-Aware Graph Neural Network
Zhang, Aihu
Xu, Jiaxing
Lan, Mengcheng
Xiang, Shili
Ke, Yiping
Machine Learning
Graph Neural Networks (GNNs) have achieved significant success in various learning tasks on graph-structured data. Nevertheless, most GNNs struggle to generalize to heterophilic neighborhoods. Additionally, many GNNs ignore the directional nature of real-world graphs, resulting in suboptimal performance on directed graphs with asymmetric structures. In this work, we propose Directed Homophily-aware Graph Neural Network (DHGNN), a novel framework that addresses these limitations by incorporating homophily-aware and direction-sensitive components. DHGNN employs a resettable gating mechanism to adaptively modulate message contributions based on homophily levels and informativeness, and a structure-aware noise-tolerant fusion module to effectively integrate node representations from the original and reverse directions. Extensive experiments on both homophilic and heterophilic directed graph datasets demonstrate that DHGNN outperforms state-of-the-art methods in node classification and link prediction. In particular, DHGNN improves over the best baseline by up to 15.07\% in link prediction. Our analysis further shows that the gating mechanism captures directional homophily gaps and fluctuating homophily across layers, providing deeper insights into message-passing behavior on complex graph structures.
title Directed Homophily-Aware Graph Neural Network
topic Machine Learning
url https://arxiv.org/abs/2505.22362