Attention-Aware Heterogeneous Graph Neural Network

As a powerful tool for elucidating the embedding representation of graph-structured data, Graph Neural Networks (GNNs), which are a series of powerful tools built on homogeneous networks, have been widely used in various data mining tasks. It is a huge challenge to apply a GNN to an embedding Hetero...

Full description

Saved in:
Bibliographic Details
Main Authors: Jintao Zhang, Quan Xu
Format: Article
Language:English
Published: Tsinghua University Press 2021-12-01
Series:Big Data Mining and Analytics
Subjects:
Online Access:https://www.sciopen.com/article/10.26599/BDMA.2021.9020008
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832572823406641152
author Jintao Zhang
Quan Xu
author_facet Jintao Zhang
Quan Xu
author_sort Jintao Zhang
collection DOAJ
description As a powerful tool for elucidating the embedding representation of graph-structured data, Graph Neural Networks (GNNs), which are a series of powerful tools built on homogeneous networks, have been widely used in various data mining tasks. It is a huge challenge to apply a GNN to an embedding Heterogeneous Information Network (HIN). The main reason for this challenge is that HINs contain many different types of nodes and different types of relationships between nodes. HIN contains rich semantic and structural information, which requires a specially designed graph neural network. However, the existing HIN-based graph neural network models rarely consider the interactive information hidden between the meta-paths of HIN in the poor embedding of nodes in the HIN. In this paper, we propose an Attention-aware Heterogeneous graph Neural Network (AHNN) model to effectively extract useful information from HIN and use it to learn the embedding representation of nodes. Specifically, we first use node-level attention to aggregate and update the embedding representation of nodes, and then concatenate the embedding representation of the nodes on different meta-paths. Finally, the semantic-level neural network is proposed to extract the feature interaction relationships on different meta-paths and learn the final embedding of nodes. Experimental results on three widely used datasets showed that the AHNN model could significantly outperform the state-of-the-art models.
format Article
id doaj-art-93533f5b959f43f4b2ba80d238848fb8
institution Kabale University
issn 2096-0654
language English
publishDate 2021-12-01
publisher Tsinghua University Press
record_format Article
series Big Data Mining and Analytics
spelling doaj-art-93533f5b959f43f4b2ba80d238848fb82025-02-02T06:50:33ZengTsinghua University PressBig Data Mining and Analytics2096-06542021-12-014423324110.26599/BDMA.2021.9020008Attention-Aware Heterogeneous Graph Neural NetworkJintao Zhang0Quan Xu1<institution>College of Sciences, Northeastern University</institution>, <city>Shenyang</city> <postal-code>110004</postal-code>, <country>China</country><institution>State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University</institution>, <city>Shenyang</city> <postal-code>110819</postal-code>, <country>China</country>As a powerful tool for elucidating the embedding representation of graph-structured data, Graph Neural Networks (GNNs), which are a series of powerful tools built on homogeneous networks, have been widely used in various data mining tasks. It is a huge challenge to apply a GNN to an embedding Heterogeneous Information Network (HIN). The main reason for this challenge is that HINs contain many different types of nodes and different types of relationships between nodes. HIN contains rich semantic and structural information, which requires a specially designed graph neural network. However, the existing HIN-based graph neural network models rarely consider the interactive information hidden between the meta-paths of HIN in the poor embedding of nodes in the HIN. In this paper, we propose an Attention-aware Heterogeneous graph Neural Network (AHNN) model to effectively extract useful information from HIN and use it to learn the embedding representation of nodes. Specifically, we first use node-level attention to aggregate and update the embedding representation of nodes, and then concatenate the embedding representation of the nodes on different meta-paths. Finally, the semantic-level neural network is proposed to extract the feature interaction relationships on different meta-paths and learn the final embedding of nodes. Experimental results on three widely used datasets showed that the AHNN model could significantly outperform the state-of-the-art models.https://www.sciopen.com/article/10.26599/BDMA.2021.9020008graph neural network (gnn)heterogeneous information network (hin)embedding
spellingShingle Jintao Zhang
Quan Xu
Attention-Aware Heterogeneous Graph Neural Network
Big Data Mining and Analytics
graph neural network (gnn)
heterogeneous information network (hin)
embedding
title Attention-Aware Heterogeneous Graph Neural Network
title_full Attention-Aware Heterogeneous Graph Neural Network
title_fullStr Attention-Aware Heterogeneous Graph Neural Network
title_full_unstemmed Attention-Aware Heterogeneous Graph Neural Network
title_short Attention-Aware Heterogeneous Graph Neural Network
title_sort attention aware heterogeneous graph neural network
topic graph neural network (gnn)
heterogeneous information network (hin)
embedding
url https://www.sciopen.com/article/10.26599/BDMA.2021.9020008
work_keys_str_mv AT jintaozhang attentionawareheterogeneousgraphneuralnetwork
AT quanxu attentionawareheterogeneousgraphneuralnetwork