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...

Full description

Saved in:
Bibliographic Details
Main Authors: LO, Pei-Chi, LIM, Ee peng
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
Description
Summary: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.