Co-embedding attributed networks with external knowledge
Attributed network embedding aims to learn representations of nodes and their attributes in a low-dimensional space that preserves their semantics. The existing embedding models, however, consider node connectivity and node attributes only while ignoring external knowledge that can enhance node repr...
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/5667 https://ink.library.smu.edu.sg/context/sis_research/article/6670/viewcontent/BIGDATA_CO_EMBEDDING_ATTRIBUTED_NETWORKS_WITH_EXTERNAL_KNOWLEDGE.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-6670 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-66702021-02-04T04:21:29Z Co-embedding attributed networks with external knowledge LO, Pei-Chi LIM, Ee peng Attributed network embedding aims to learn representations of nodes and their attributes in a low-dimensional space that preserves their semantics. The existing embedding models, however, consider node connectivity and node attributes only while ignoring external knowledge that can enhance node representations for downstream applications. In this paper, we propose a set of new VAE-based embedding models called External Knowledge-Aware Co-Embedding Attributed Network (ECAN) Embeddings to incorporate associations among attributes from relevant external knowledge. Such external knowledge can be extracted from text corpus and knowledge graphs. We use multi-VAE structures to model the attribute associations. To cope with joint encoding of attribute semantics from different sources, we introduce a mixed model variant which has a twolayer encoder structure. Our experiments on three real-world datasets show that ECAN out-performs previous approaches in both node classification and link prediction tasks. 2020-12-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/5667 https://ink.library.smu.edu.sg/context/sis_research/article/6670/viewcontent/BIGDATA_CO_EMBEDDING_ATTRIBUTED_NETWORKS_WITH_EXTERNAL_KNOWLEDGE.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 Attributed Networks Network Embedding Knowledge Graph Computer Sciences Databases and Information Systems |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Attributed Networks Network Embedding Knowledge Graph Computer Sciences Databases and Information Systems |
spellingShingle |
Attributed Networks Network Embedding Knowledge Graph Computer Sciences Databases and Information Systems LO, Pei-Chi LIM, Ee peng Co-embedding attributed networks with external knowledge |
description |
Attributed network embedding aims to learn representations of nodes and their attributes in a low-dimensional space that preserves their semantics. The existing embedding models, however, consider node connectivity and node attributes only while ignoring external knowledge that can enhance node representations for downstream applications. In this paper, we propose a set of new VAE-based embedding models called External Knowledge-Aware Co-Embedding Attributed Network (ECAN) Embeddings to incorporate associations among attributes from relevant external knowledge. Such external knowledge can be extracted from text corpus and knowledge graphs. We use multi-VAE structures to model the attribute associations. To cope with joint encoding of attribute semantics from different sources, we introduce a mixed model variant which has a twolayer encoder structure. Our experiments on three real-world datasets show that ECAN out-performs previous approaches in both node classification and link prediction tasks. |
format |
text |
author |
LO, Pei-Chi LIM, Ee peng |
author_facet |
LO, Pei-Chi LIM, Ee peng |
author_sort |
LO, Pei-Chi |
title |
Co-embedding attributed networks with external knowledge |
title_short |
Co-embedding attributed networks with external knowledge |
title_full |
Co-embedding attributed networks with external knowledge |
title_fullStr |
Co-embedding attributed networks with external knowledge |
title_full_unstemmed |
Co-embedding attributed networks with external knowledge |
title_sort |
co-embedding attributed networks with external knowledge |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2020 |
url |
https://ink.library.smu.edu.sg/sis_research/5667 https://ink.library.smu.edu.sg/context/sis_research/article/6670/viewcontent/BIGDATA_CO_EMBEDDING_ATTRIBUTED_NETWORKS_WITH_EXTERNAL_KNOWLEDGE.PDF |
_version_ |
1770575556944855040 |