When convolutional network meets temporal heterogeneous graphs: an effective community detection method

Community detection has long been an important yet challenging task to analyze complex networks with a focus on detecting topological structures of graph data. Essentially, real-world graph data is generally heterogeneous which dynamically varies over time, and this invalidates most existing communi...

Full description

Saved in:
Bibliographic Details
Main Authors: Zheng, Yaping, Zhang, Xiaofeng, Chen, Shiyi, Zhang, Xinni, Yang, Xiaofei, Wang, Di
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2023
Subjects:
Online Access:https://hdl.handle.net/10356/172861
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-172861
record_format dspace
spelling sg-ntu-dr.10356-1728612023-12-27T02:34:51Z When convolutional network meets temporal heterogeneous graphs: an effective community detection method Zheng, Yaping Zhang, Xiaofeng Chen, Shiyi Zhang, Xinni Yang, Xiaofei Wang, Di School of Computer Science and Engineering Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly (LILY) Engineering::Computer science and engineering Graph Convolutional Network Heterogeneous Graph Community detection has long been an important yet challenging task to analyze complex networks with a focus on detecting topological structures of graph data. Essentially, real-world graph data is generally heterogeneous which dynamically varies over time, and this invalidates most existing community detection approaches. To cope with these issues, this paper proposes the temporal-heterogeneous graph convolutional networks (THGCN) to detect communities using the learnt feature representations of a set of temporal heterogeneous graphs. Particularly, we first design a heterogeneous GCN component to represent features of heterogeneous graph at each time step. Then, a residual compressed aggregation component is proposed to learn temporal feature representations extracted from two consecutive heterogeneous graphs. These temporal features are considered to contain evolutionary patterns of underlying communities. To the best of our knowledge, this is the first attempt to detect communities from temporal heterogeneous graphs. To evaluate the model performance, extensive experiments are performed on two real-world datasets, i.e., DBLP and IMDB. The promising results have demonstrated that the proposed THGCN is superior to both benchmark and the state-of-the-art approaches, e.g., GCN, GAT, GNN, LGNN, HAN and STAR, with respect to a number of evaluation criteria. This work was supported in part by the National Key Research and Development Program of China under Grants 2018YFB1003800 and 2018YFB1003804, the National Natural Science Foundation of China under Grants 61872108, and the Shenzhen Science and Technology Program under Grant No. JCYJ20200109113201726 and JCYJ20170811153507788. 2023-12-27T02:34:51Z 2023-12-27T02:34:51Z 2023 Journal Article Zheng, Y., Zhang, X., Chen, S., Zhang, X., Yang, X. & Wang, D. (2023). When convolutional network meets temporal heterogeneous graphs: an effective community detection method. IEEE Transactions On Knowledge and Data Engineering, 35(2), 2173-2178. https://dx.doi.org/10.1109/TKDE.2021.3096122 1041-4347 https://hdl.handle.net/10356/172861 10.1109/TKDE.2021.3096122 2-s2.0-85147510518 2 35 2173 2178 en IEEE Transactions on Knowledge and Data Engineering © 2021 IEEE. All rights reserved.
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Computer science and engineering
Graph Convolutional Network
Heterogeneous Graph
spellingShingle Engineering::Computer science and engineering
Graph Convolutional Network
Heterogeneous Graph
Zheng, Yaping
Zhang, Xiaofeng
Chen, Shiyi
Zhang, Xinni
Yang, Xiaofei
Wang, Di
When convolutional network meets temporal heterogeneous graphs: an effective community detection method
description Community detection has long been an important yet challenging task to analyze complex networks with a focus on detecting topological structures of graph data. Essentially, real-world graph data is generally heterogeneous which dynamically varies over time, and this invalidates most existing community detection approaches. To cope with these issues, this paper proposes the temporal-heterogeneous graph convolutional networks (THGCN) to detect communities using the learnt feature representations of a set of temporal heterogeneous graphs. Particularly, we first design a heterogeneous GCN component to represent features of heterogeneous graph at each time step. Then, a residual compressed aggregation component is proposed to learn temporal feature representations extracted from two consecutive heterogeneous graphs. These temporal features are considered to contain evolutionary patterns of underlying communities. To the best of our knowledge, this is the first attempt to detect communities from temporal heterogeneous graphs. To evaluate the model performance, extensive experiments are performed on two real-world datasets, i.e., DBLP and IMDB. The promising results have demonstrated that the proposed THGCN is superior to both benchmark and the state-of-the-art approaches, e.g., GCN, GAT, GNN, LGNN, HAN and STAR, with respect to a number of evaluation criteria.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Zheng, Yaping
Zhang, Xiaofeng
Chen, Shiyi
Zhang, Xinni
Yang, Xiaofei
Wang, Di
format Article
author Zheng, Yaping
Zhang, Xiaofeng
Chen, Shiyi
Zhang, Xinni
Yang, Xiaofei
Wang, Di
author_sort Zheng, Yaping
title When convolutional network meets temporal heterogeneous graphs: an effective community detection method
title_short When convolutional network meets temporal heterogeneous graphs: an effective community detection method
title_full When convolutional network meets temporal heterogeneous graphs: an effective community detection method
title_fullStr When convolutional network meets temporal heterogeneous graphs: an effective community detection method
title_full_unstemmed When convolutional network meets temporal heterogeneous graphs: an effective community detection method
title_sort when convolutional network meets temporal heterogeneous graphs: an effective community detection method
publishDate 2023
url https://hdl.handle.net/10356/172861
_version_ 1787136490775511040