An Information-Explainable Random Walk Based Unsupervised Network Representation Learning Framework on Node Classification Tasks

Xin Xu, Yang Lu, Yupeng Zhou, Zhiguo Fu, Yanjie Fu and Minghao Yin
Additional contact information
Xin Xu: Department of Computer Science, College of Information Science and Technology, Northeast Normal University, Changchun 130117, China
Yang Lu: Department of Computer Science, College of Information Science and Technology, Northeast Normal University, Changchun 130117, China
Yupeng Zhou: Department of Computer Science, College of Information Science and Technology, Northeast Normal University, Changchun 130117, China
Zhiguo Fu: Department of Computer Science, College of Information Science and Technology, Northeast Normal University, Changchun 130117, China
Yanjie Fu: Department of Computer Science, College of Engineering and Computer Science, University of Central Florida, Orlando, FL 32816, USA
Minghao Yin: Department of Computer Science, College of Information Science and Technology, Northeast Normal University, Changchun 130117, China

Mathematics, 2021, vol. 9, issue 15, 1-14

Abstract: Network representation learning aims to learn low-dimensional, compressible, and distributed representational vectors of nodes in networks. Due to the expensive costs of obtaining label information of nodes in networks, many unsupervised network representation learning methods have been proposed, where random walk strategy is one of the wildly utilized approaches. However, the existing random walk based methods have some challenges, including: 1. The insufficiency of explaining what network knowledge in the walking path-samplings; 2. The adverse effects caused by the mixture of different information in networks; 3. The poor generality of the methods with hyper-parameters on different networks. This paper proposes an information-explainable random walk based unsupervised network representation learning framework named Probabilistic Accepted Walk (PAW) to obtain network representation from the perspective of the stationary distribution of networks. In the framework, we design two stationary distributions based on nodes’ self-information and local-information of networks to guide our proposed random walk strategy to learn representational vectors of networks through sampling paths of nodes. Numerous experimental results demonstrated that the PAW could obtain more expressive representation than the other six widely used unsupervised network representation learning baselines on four real-world networks in single-label and multi-label node classification tasks.

Keywords: network representation learning; random walk; stationary distributions; unsupervised learning; network embedding (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/9/15/1767/pdf (application/pdf)
https://www.mdpi.com/2227-7390/9/15/1767/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:9:y:2021:i:15:p:1767-:d:601994

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().