Network representation learning guided by partial community structure

Sun, Hanlin, Jie, Wei ORCID:, Wang, Zhongmin, Wang, Hai and Ma, Sugang (2020) Network representation learning guided by partial community structure. IEEE Access, 8. pp. 46665-46681.

[thumbnail of PDF/A format]
PDF (PDF/A format)
Jie_etal_2020_IEEE_Access_Network_representation_learning_guided_by_partial_community_structure.pdf - Accepted Version
Available under License Creative Commons Attribution.

Download (1MB) | Preview
[thumbnail of Jie_etal_2020_IEEE_Access_Network_representation_learning_guided_by_partial_community_structure_published_version.pdf]
Jie_etal_2020_IEEE_Access_Network_representation_learning_guided_by_partial_community_structure_published_version.pdf - Published Version
Available under License Creative Commons Attribution.

Download (6MB) | Preview


Network Representation Learning (NRL) is an effective way to analyse large scale networks (graphs). In general, it maps network nodes, edges, subgraphs, etc. onto independent vectors in a low dimension space, thus facilitating network analysis tasks. As community structure is one of the most prominent mesoscopic structure properties of real networks, it is necessary to preserve community structure of networks during NRL. In this paper, the concept of k-step partial community structure is defined and two Partial Community structure Guided Network Embedding (PCGNE) methods, based on two popular NRL algorithms (DeepWalk and node2vec respectively), for node representation learning are proposed. The idea behind this is that it is easier and more cost-effective to find a higher quality 1-step partial community structure than a higher quality whole community structure for networks; the extracted partial community information is then used to guide random walks in DeepWalk or node2vec. As a result, the learned node representations could preserve community structure property of networks more effectively. The two proposed algorithms and six state-of-the-art NRL algorithms were examined through multi-label classification and (inner community) link prediction on eight synthesized networks: one where community structure property could be controlled, and one real world network. The results suggested that the two PCGNE methods could improve the performance of their own based algorithm significantly and were competitive for node representation learning. Especially, comparing against used baseline algorithms, PCGNE methods could capture overlapping community structure much better, and thus could achieve better performance for multi-label classification on networks that have more overlapping nodes and/or larger overlapping memberships.

Item Type: Article
Identifier: 10.1109/access.2020.2978517
Additional Information: This work was partially supported by the National Natural Science Foundation of China [No. 61702414]; the International Science and Technology Cooperation Project of Shaanxi Province, China [No. 2019KW-008]; the Key Industry Innovation Chain Project of Shaanxi Province, China [No. 2019ZDLGY07-08]
Keywords: network embedding, network representation learning, partial community structure, community structure, multi-label classification, link prediction
Subjects: Computing > Information management
Computing > Intelligent systems
Computing > Systems
Related URLs:
Depositing User: WEI JIE
Date Deposited: 28 Feb 2020 20:44
Last Modified: 06 Feb 2024 16:02


Downloads per month over past year

Actions (login required)

View Item View Item