Signed Network Embedding with Dynamic Metric Learning
Network embedding is an important method to learn low-dimensional vector representations of nodes in networks, which has wide-ranging applications in network analysis such as link prediction. Most existing network embedding models focus on the unsigned networks with only positive links. However, net...
Published in: | 2020 International Wireless Communications and Mobile Computing (IWCMC) |
---|---|
Main Authors: | , , , , |
Format: | Conference Object |
Language: | English |
Published: |
Institute of Electrical and Electronics Engineers Inc.
|
Subjects: | |
Online Access: | http://hdl.handle.net/10576/36938 https://doi.org/10.1109/IWCMC48107.2020.9148129 https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85089696799&origin=inward |
id |
ftqataruniv:oai:qspace.qu.edu.qa:10576/36938 |
---|---|
record_format |
openpolar |
spelling |
ftqataruniv:oai:qspace.qu.edu.qa:10576/36938 2024-09-09T19:38:13+00:00 Signed Network Embedding with Dynamic Metric Learning Wu, H. Guan, Donghai Han, Guangjie Yuan, Weiwei Guizani, Mohsen http://hdl.handle.net/10576/36938 https://doi.org/10.1109/IWCMC48107.2020.9148129 https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85089696799&origin=inward en eng Institute of Electrical and Electronics Engineers Inc. http://dx.doi.org/10.1109/IWCMC48107.2020.9148129 Wu, H., Guan, D., Han, G., Yuan, W., & Guizani, M. (2020, June). Signed Network Embedding with Dynamic Metric Learning. In 2020 International Wireless Communications and Mobile Computing (IWCMC) (pp. 533-538). IEEE. 9781728131290 https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85089696799&origin=inward http://hdl.handle.net/10576/36938 533-538 dynamic metric learning sign prediction Signed network embedding Conference Paper ftqataruniv https://doi.org/10.1109/IWCMC48107.2020.9148129 2024-07-30T14:28:48Z Network embedding is an important method to learn low-dimensional vector representations of nodes in networks, which has wide-ranging applications in network analysis such as link prediction. Most existing network embedding models focus on the unsigned networks with only positive links. However, networks should have both positive and negative links in practical applications such as the trust and distrust relationships in social networks. It is certain that there are different properties between positive links and negative links, which means the network embedding models designed for unsigned networks are not suitable for signed networks. In this paper, we propose SNE-DML, a signed network embedding model with dynamic metric learning. The model learns positive and negative distance metrics respectively in the training process. We conduct sign prediction experiments on three datasets and compare with seven baselines including three signed network embedding models and four state-of-the-art unsigned network embedding models. The experimental results show the effectiveness of our model. This research was supported by Nature Science Foundation of China (Grant No. 61672284), Nature Science Foundation of Jiangsu Province (Grant No. BK20171418), China Postdoctoral Science Foundation (Grant No. 2016M591841) and Jiangsu Planned Projects for Postdoctoral Research Funds (No. 1601225C). Conference Object DML Qatar University: QU Institutional Repository 2020 International Wireless Communications and Mobile Computing (IWCMC) 533 538 |
institution |
Open Polar |
collection |
Qatar University: QU Institutional Repository |
op_collection_id |
ftqataruniv |
language |
English |
topic |
dynamic metric learning sign prediction Signed network embedding |
spellingShingle |
dynamic metric learning sign prediction Signed network embedding Wu, H. Guan, Donghai Han, Guangjie Yuan, Weiwei Guizani, Mohsen Signed Network Embedding with Dynamic Metric Learning |
topic_facet |
dynamic metric learning sign prediction Signed network embedding |
description |
Network embedding is an important method to learn low-dimensional vector representations of nodes in networks, which has wide-ranging applications in network analysis such as link prediction. Most existing network embedding models focus on the unsigned networks with only positive links. However, networks should have both positive and negative links in practical applications such as the trust and distrust relationships in social networks. It is certain that there are different properties between positive links and negative links, which means the network embedding models designed for unsigned networks are not suitable for signed networks. In this paper, we propose SNE-DML, a signed network embedding model with dynamic metric learning. The model learns positive and negative distance metrics respectively in the training process. We conduct sign prediction experiments on three datasets and compare with seven baselines including three signed network embedding models and four state-of-the-art unsigned network embedding models. The experimental results show the effectiveness of our model. This research was supported by Nature Science Foundation of China (Grant No. 61672284), Nature Science Foundation of Jiangsu Province (Grant No. BK20171418), China Postdoctoral Science Foundation (Grant No. 2016M591841) and Jiangsu Planned Projects for Postdoctoral Research Funds (No. 1601225C). |
format |
Conference Object |
author |
Wu, H. Guan, Donghai Han, Guangjie Yuan, Weiwei Guizani, Mohsen |
author_facet |
Wu, H. Guan, Donghai Han, Guangjie Yuan, Weiwei Guizani, Mohsen |
author_sort |
Wu, H. |
title |
Signed Network Embedding with Dynamic Metric Learning |
title_short |
Signed Network Embedding with Dynamic Metric Learning |
title_full |
Signed Network Embedding with Dynamic Metric Learning |
title_fullStr |
Signed Network Embedding with Dynamic Metric Learning |
title_full_unstemmed |
Signed Network Embedding with Dynamic Metric Learning |
title_sort |
signed network embedding with dynamic metric learning |
publisher |
Institute of Electrical and Electronics Engineers Inc. |
url |
http://hdl.handle.net/10576/36938 https://doi.org/10.1109/IWCMC48107.2020.9148129 https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85089696799&origin=inward |
genre |
DML |
genre_facet |
DML |
op_relation |
http://dx.doi.org/10.1109/IWCMC48107.2020.9148129 Wu, H., Guan, D., Han, G., Yuan, W., & Guizani, M. (2020, June). Signed Network Embedding with Dynamic Metric Learning. In 2020 International Wireless Communications and Mobile Computing (IWCMC) (pp. 533-538). IEEE. 9781728131290 https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85089696799&origin=inward http://hdl.handle.net/10576/36938 533-538 |
op_doi |
https://doi.org/10.1109/IWCMC48107.2020.9148129 |
container_title |
2020 International Wireless Communications and Mobile Computing (IWCMC) |
container_start_page |
533 |
op_container_end_page |
538 |
_version_ |
1809907186282790912 |