BiANE: Bipartite Attributed Network Embedding
Network embedding effectively transforms complex network data into a low-dimensional vector space and has shown great performance in many real-world scenarios, such as link prediction, node classification, and similarity search. A plethora of methods have been proposed to learn node representations...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2020
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/5280 https://ink.library.smu.edu.sg/context/sis_research/article/6283/viewcontent/SIGIR20_BiANE.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-6283 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-62832020-09-09T05:00:08Z BiANE: Bipartite Attributed Network Embedding HUANG, Wentao LI, Yuchen FANG, Yuan FAN, Ju YANG, Hongxia Network embedding effectively transforms complex network data into a low-dimensional vector space and has shown great performance in many real-world scenarios, such as link prediction, node classification, and similarity search. A plethora of methods have been proposed to learn node representations and achieve encouraging results. Nevertheless, little attention has been paid on the embedding technique for bipartite attributed networks, which is a typical data structure for modeling nodes from two distinct partitions. In this paper, we propose a novel model called BiANE, short for Bipartite Attributed Network Embedding. In particular, BiANE not only models the inter-partition proximity but also models the intra-partition proximity. To effectively preserve the intra-partition proximity, we jointly model the attribute proximity and the structure proximity through a novel latent correlation training approach. Furthermore, we propose a dynamic positive sampling technique to overcome the efficiency drawbacks of the existing dynamic negative sampling techniques. Extensive experiments have been conducted on several real-world networks, and the results demonstrate that our proposed approach can significantly outperform state-of-theart methods. 2020-07-01T07:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/5280 info:doi/10.1145/3397271.3401068 https://ink.library.smu.edu.sg/context/sis_research/article/6283/viewcontent/SIGIR20_BiANE.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Network embedding Bipartite attributed network Link prediction Databases and Information Systems OS and Networks |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Network embedding Bipartite attributed network Link prediction Databases and Information Systems OS and Networks |
spellingShingle |
Network embedding Bipartite attributed network Link prediction Databases and Information Systems OS and Networks HUANG, Wentao LI, Yuchen FANG, Yuan FAN, Ju YANG, Hongxia BiANE: Bipartite Attributed Network Embedding |
description |
Network embedding effectively transforms complex network data into a low-dimensional vector space and has shown great performance in many real-world scenarios, such as link prediction, node classification, and similarity search. A plethora of methods have been proposed to learn node representations and achieve encouraging results. Nevertheless, little attention has been paid on the embedding technique for bipartite attributed networks, which is a typical data structure for modeling nodes from two distinct partitions. In this paper, we propose a novel model called BiANE, short for Bipartite Attributed Network Embedding. In particular, BiANE not only models the inter-partition proximity but also models the intra-partition proximity. To effectively preserve the intra-partition proximity, we jointly model the attribute proximity and the structure proximity through a novel latent correlation training approach. Furthermore, we propose a dynamic positive sampling technique to overcome the efficiency drawbacks of the existing dynamic negative sampling techniques. Extensive experiments have been conducted on several real-world networks, and the results demonstrate that our proposed approach can significantly outperform state-of-theart methods. |
format |
text |
author |
HUANG, Wentao LI, Yuchen FANG, Yuan FAN, Ju YANG, Hongxia |
author_facet |
HUANG, Wentao LI, Yuchen FANG, Yuan FAN, Ju YANG, Hongxia |
author_sort |
HUANG, Wentao |
title |
BiANE: Bipartite Attributed Network Embedding |
title_short |
BiANE: Bipartite Attributed Network Embedding |
title_full |
BiANE: Bipartite Attributed Network Embedding |
title_fullStr |
BiANE: Bipartite Attributed Network Embedding |
title_full_unstemmed |
BiANE: Bipartite Attributed Network Embedding |
title_sort |
biane: bipartite attributed network embedding |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2020 |
url |
https://ink.library.smu.edu.sg/sis_research/5280 https://ink.library.smu.edu.sg/context/sis_research/article/6283/viewcontent/SIGIR20_BiANE.pdf |
_version_ |
1770575369506652160 |