ReAHGN: Adaptive Heterogeneous Graph Neural Network With Relation-Aware Embedding

Heterogeneous graph neural networks (HGNs) have attracted more and more attention recently due to their wide applications such as node classification, community detection, and recommendation. Significant progress has been made by graph neural networks. However, we argue that attention mechanisms tha...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaoyu Zhu, Xinzhe Yu, Enze Zha, Shiyang Lin
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10918934/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850041287318700032
author Xiaoyu Zhu
Xinzhe Yu
Enze Zha
Shiyang Lin
author_facet Xiaoyu Zhu
Xinzhe Yu
Enze Zha
Shiyang Lin
author_sort Xiaoyu Zhu
collection DOAJ
description Heterogeneous graph neural networks (HGNs) have attracted more and more attention recently due to their wide applications such as node classification, community detection, and recommendation. Significant progress has been made by graph neural networks. However, we argue that attention mechanisms that focus on computing higher ranking scores for specific types of nodes cannot select the most relevant neighbors for any target node. To enhance the expressiveness of the HGNs, we propose ReAHGN, a Relation-aware embedding for Adaptive Heterogeneous Graph Neural Network. Specifically, we present an adaptive attention mechanism that assigns different weights for each type of target node automatically. In addition, a relation-aware embedding method is adopted to fuse the edge type information effectively. ReAHGN is evaluated for three downstream tasks and on ten public datasets. Experiment results demonstrate that ReAHGN can outperform the state-of-the-art HGNs.
format Article
id doaj-art-394bdc439daa4803bf61ee5459b99b98
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-394bdc439daa4803bf61ee5459b99b982025-08-20T02:55:49ZengIEEEIEEE Access2169-35362025-01-0113449514496210.1109/ACCESS.2025.354992810918934ReAHGN: Adaptive Heterogeneous Graph Neural Network With Relation-Aware EmbeddingXiaoyu Zhu0Xinzhe Yu1Enze Zha2https://orcid.org/0009-0005-1546-2210Shiyang Lin3https://orcid.org/0000-0003-1498-4226China Offshore Fugro Geosolutions (Shenzhen) Company Ltd., Nanshan, Shenzhen, Guangdong, ChinaChina Offshore Fugro Geosolutions (Shenzhen) Company Ltd., Nanshan, Shenzhen, Guangdong, ChinaSchool of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen, ChinaSchool of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen, ChinaHeterogeneous graph neural networks (HGNs) have attracted more and more attention recently due to their wide applications such as node classification, community detection, and recommendation. Significant progress has been made by graph neural networks. However, we argue that attention mechanisms that focus on computing higher ranking scores for specific types of nodes cannot select the most relevant neighbors for any target node. To enhance the expressiveness of the HGNs, we propose ReAHGN, a Relation-aware embedding for Adaptive Heterogeneous Graph Neural Network. Specifically, we present an adaptive attention mechanism that assigns different weights for each type of target node automatically. In addition, a relation-aware embedding method is adopted to fuse the edge type information effectively. ReAHGN is evaluated for three downstream tasks and on ten public datasets. Experiment results demonstrate that ReAHGN can outperform the state-of-the-art HGNs.https://ieeexplore.ieee.org/document/10918934/Graph neural networkheterogeneous graph neural networksgraph representation learning
spellingShingle Xiaoyu Zhu
Xinzhe Yu
Enze Zha
Shiyang Lin
ReAHGN: Adaptive Heterogeneous Graph Neural Network With Relation-Aware Embedding
IEEE Access
Graph neural network
heterogeneous graph neural networks
graph representation learning
title ReAHGN: Adaptive Heterogeneous Graph Neural Network With Relation-Aware Embedding
title_full ReAHGN: Adaptive Heterogeneous Graph Neural Network With Relation-Aware Embedding
title_fullStr ReAHGN: Adaptive Heterogeneous Graph Neural Network With Relation-Aware Embedding
title_full_unstemmed ReAHGN: Adaptive Heterogeneous Graph Neural Network With Relation-Aware Embedding
title_short ReAHGN: Adaptive Heterogeneous Graph Neural Network With Relation-Aware Embedding
title_sort reahgn adaptive heterogeneous graph neural network with relation aware embedding
topic Graph neural network
heterogeneous graph neural networks
graph representation learning
url https://ieeexplore.ieee.org/document/10918934/
work_keys_str_mv AT xiaoyuzhu reahgnadaptiveheterogeneousgraphneuralnetworkwithrelationawareembedding
AT xinzheyu reahgnadaptiveheterogeneousgraphneuralnetworkwithrelationawareembedding
AT enzezha reahgnadaptiveheterogeneousgraphneuralnetworkwithrelationawareembedding
AT shiyanglin reahgnadaptiveheterogeneousgraphneuralnetworkwithrelationawareembedding