Network Representation Learning Guided by Partial Community Structure
- Submitting institution
-
The University of West London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 11024
- Type
- D - Journal article
- DOI
-
10.1109/ACCESS.2020.2978517
- Title of journal
- IEEE Access
- Article number
- -
- First page
- 46665
- Volume
- 8
- Issue
- -
- ISSN
- 2169-3536
- Open access status
- Compliant
- Month of publication
- -
- Year of publication
- 2020
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
4
- Research group(s)
-
-
- Citation count
- 0
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This work is partially funded by top funding body in China - National Natural Science Foundation (No. 61702414), and the International Science and Technology Cooperation Project of Shaanxi Province in China (No.2019KW-008). This paper presents the very first community detection and analysis algorithm based on Network Representation Learning model. Extensive experiments on both synthesized and real networks (e.g. Yahoo! Flickr) were conducted. The results show, compared ato the popular algorithms, the proposed algorithm performs significantly better on capturing overlapping community structure, and achieves better performance for multi-label classification on networks that have more overlapping nodes and/or larger overlapping memberships.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -