Attributed social network embedding

Embedding network data into a low-dimensional vector space has shown promising performance for many real-world applications, such as node classification and entity retrieval. However, most existing methods focused only on leveraging network structure. For social networks, besides the network structu...

Full description

Saved in:
Bibliographic Details
Main Authors: Liao, Lizi, He, Xiangnan, Zhang, Hanwang, Chua, Tat-Seng
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2020
Subjects:
Online Access:https://hdl.handle.net/10356/140794
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-140794
record_format dspace
spelling sg-ntu-dr.10356-1407942020-06-02T04:00:39Z Attributed social network embedding Liao, Lizi He, Xiangnan Zhang, Hanwang Chua, Tat-Seng School of Computer Science and Engineering Engineering::Computer science and engineering Social Network Representation Homophily Embedding network data into a low-dimensional vector space has shown promising performance for many real-world applications, such as node classification and entity retrieval. However, most existing methods focused only on leveraging network structure. For social networks, besides the network structure, there also exists rich information about social actors, such as user profiles of friendship networks and textual content of citation networks. These rich attribute information of social actors reveal the homophily effect, exerting huge impacts on the formation of social networks. In this paper, we explore the rich evidence source of attributes in social networks to improve network embedding. We propose a generic Attributed Social Network Embedding framework (ASNE), which learns representations for social actors (i.e., nodes) by preserving both the structural proximity and attribute proximity. While the structural proximity captures the global network structure, the attribute proximity accounts for the homophily effect. To justify our proposal, we conduct extensive experiments on four real-world social networks. Compared to the state-of-the-art network embedding approaches, ASNE can learn more informative representations, achieving substantial gains on the tasks of link prediction and node classification. Specifically, ASNE significantly outperforms node2vec with an 8.2 percent relative improvement on the link prediction task, and a 12.7 percent gain on the node classification task. NRF (Natl Research Foundation, S’pore) 2020-06-02T04:00:39Z 2020-06-02T04:00:39Z 2018 Journal Article Liao, L., He, X., Zhang, H., & Chua, T.-S. (2018). Attributed social network embedding. IEEE Transactions on Knowledge and Data Engineering, 30(12), 2257-2270. doi:10.1109/tkde.2018.2819980 1041-4347 https://hdl.handle.net/10356/140794 10.1109/TKDE.2018.2819980 2-s2.0-85044860469 12 30 2257 2270 en IEEE Transactions on Knowledge and Data Engineering © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/TKDE.2018.2819980
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic Engineering::Computer science and engineering
Social Network Representation
Homophily
spellingShingle Engineering::Computer science and engineering
Social Network Representation
Homophily
Liao, Lizi
He, Xiangnan
Zhang, Hanwang
Chua, Tat-Seng
Attributed social network embedding
description Embedding network data into a low-dimensional vector space has shown promising performance for many real-world applications, such as node classification and entity retrieval. However, most existing methods focused only on leveraging network structure. For social networks, besides the network structure, there also exists rich information about social actors, such as user profiles of friendship networks and textual content of citation networks. These rich attribute information of social actors reveal the homophily effect, exerting huge impacts on the formation of social networks. In this paper, we explore the rich evidence source of attributes in social networks to improve network embedding. We propose a generic Attributed Social Network Embedding framework (ASNE), which learns representations for social actors (i.e., nodes) by preserving both the structural proximity and attribute proximity. While the structural proximity captures the global network structure, the attribute proximity accounts for the homophily effect. To justify our proposal, we conduct extensive experiments on four real-world social networks. Compared to the state-of-the-art network embedding approaches, ASNE can learn more informative representations, achieving substantial gains on the tasks of link prediction and node classification. Specifically, ASNE significantly outperforms node2vec with an 8.2 percent relative improvement on the link prediction task, and a 12.7 percent gain on the node classification task.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Liao, Lizi
He, Xiangnan
Zhang, Hanwang
Chua, Tat-Seng
format Article
author Liao, Lizi
He, Xiangnan
Zhang, Hanwang
Chua, Tat-Seng
author_sort Liao, Lizi
title Attributed social network embedding
title_short Attributed social network embedding
title_full Attributed social network embedding
title_fullStr Attributed social network embedding
title_full_unstemmed Attributed social network embedding
title_sort attributed social network embedding
publishDate 2020
url https://hdl.handle.net/10356/140794
_version_ 1681056802709438464