Structural Hierarchy-Enhanced Network Representation Learning

Network representation learning (NRL) is crucial in generating effective node features for downstream tasks, such as node classification (NC) and link prediction (LP). However, existing NRL methods neither properly identify neighbor nodes that should be pushed together and away in the embedding spac...

Full description

Saved in:
Bibliographic Details
Published inApplied sciences Vol. 10; no. 20; p. 7214
Main Authors Li, Cheng-Te, Lin, Hong-Yu
Format Journal Article
LanguageEnglish
Published Basel MDPI AG 01.10.2020
Subjects
Algorithms
community detection
Data mining
Graphs
link prediction
Machine learning
Methods
network representation learning
Network topologies
node classification
node embeddings
Nodes
Representations
Semantics
Structural hierarchy
Taxonomy
Topology
Taiwan
Online AccessGet full text

Cover

More Information
Summary:Network representation learning (NRL) is crucial in generating effective node features for downstream tasks, such as node classification (NC) and link prediction (LP). However, existing NRL methods neither properly identify neighbor nodes that should be pushed together and away in the embedding space, nor model coarse-grained community knowledge hidden behind the network topology. In this paper, we propose a novel NRL framework, Structural Hierarchy Enhancement (SHE), to deal with such two issues. The main idea is to construct a structural hierarchy from the network based on community detection, and to utilize such a hierarchy to perform level-wise NRL. In addition, lower-level node embeddings are passed to higher-level ones so that community knowledge can be aware of in NRL. Experiments conducted on benchmark network datasets show that SHE can significantly boost the performance of NRL in both tasks of NC and LP, compared to other hierarchical NRL methods.
ISSN:2076-3417
2076-3417
DOI:10.3390/app10207214