Network Representation Learning Enhanced by Partial Community Information That Is Found Using Game Theory
Presently, data that are collected from real systems and organized as information networks are universal. Mining hidden information from these data is generally helpful to understand and benefit the corresponding systems. The challenges of analyzing such data include high computational complexity an...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-04-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/12/5/186 |
| _version_ | 1797536337545396224 |
|---|---|
| author | Hanlin Sun Wei Jie Jonathan Loo Liang Chen Zhongmin Wang Sugang Ma Gang Li Shuai Zhang |
| author_facet | Hanlin Sun Wei Jie Jonathan Loo Liang Chen Zhongmin Wang Sugang Ma Gang Li Shuai Zhang |
| author_sort | Hanlin Sun |
| collection | DOAJ |
| description | Presently, data that are collected from real systems and organized as information networks are universal. Mining hidden information from these data is generally helpful to understand and benefit the corresponding systems. The challenges of analyzing such data include high computational complexity and low parallelizability because of the nature of complicated interconnected structure of their nodes. Network representation learning, also called network embedding, provides a practical and promising way to solve these issues. One of the foremost requirements of network embedding is preserving network topology properties in learned low-dimension representations. Community structure is a prominent characteristic of complex networks and thus should be well maintained. However, the difficulty lies in the fact that the properties of community structure are multivariate and complicated; therefore, it is insufficient to model community structure using a predefined model, the way that is popular in most state-of-the-art network embedding algorithms explicitly considering community structure preservation. In this paper, we introduce a multi-process parallel framework for network embedding that is enhanced by found partial community information and can preserve community properties well. We also implement the framework and propose two node embedding methods that use game theory for detecting partial community information. A series of experiments are conducted to evaluate the performance of our methods and six state-of-the-art algorithms. The results demonstrate that our methods can effectively preserve community properties of networks in their low-dimension representations. Specifically, compared to the involved baselines, our algorithms behave the best and are the runners-up on networks with high overlapping diversity and density. |
| first_indexed | 2024-03-10T11:59:15Z |
| format | Article |
| id | doaj.art-bfe1626a2ca24dde9dc9137dbcb4ba4f |
| institution | Directory Open Access Journal |
| issn | 2078-2489 |
| language | English |
| last_indexed | 2024-03-10T11:59:15Z |
| publishDate | 2021-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj.art-bfe1626a2ca24dde9dc9137dbcb4ba4f2023-11-21T17:07:09ZengMDPI AGInformation2078-24892021-04-0112518610.3390/info12050186Network Representation Learning Enhanced by Partial Community Information That Is Found Using Game TheoryHanlin Sun0Wei Jie1Jonathan Loo2Liang Chen3Zhongmin Wang4Sugang Ma5Gang Li6Shuai Zhang7School of Computer Science and Technology, Xi’an University of Posts and Telecommunications, Xi’an 710121, ChinaSchool of Computing and Engineering, University of West London, London W5 5RF, UKSchool of Computing and Engineering, University of West London, London W5 5RF, UKSchool of Computing and Engineering, University of West London, London W5 5RF, UKSchool of Computer Science and Technology, Xi’an University of Posts and Telecommunications, Xi’an 710121, ChinaSchool of Electronic Engineering, Xi’an University of Posts and Telecommunications, Xi’an 710121, ChinaSchool of Computer Science and Technology, Xi’an University of Posts and Telecommunications, Xi’an 710121, ChinaSchool of Computer Science and Technology, Xi’an University of Posts and Telecommunications, Xi’an 710121, ChinaPresently, data that are collected from real systems and organized as information networks are universal. Mining hidden information from these data is generally helpful to understand and benefit the corresponding systems. The challenges of analyzing such data include high computational complexity and low parallelizability because of the nature of complicated interconnected structure of their nodes. Network representation learning, also called network embedding, provides a practical and promising way to solve these issues. One of the foremost requirements of network embedding is preserving network topology properties in learned low-dimension representations. Community structure is a prominent characteristic of complex networks and thus should be well maintained. However, the difficulty lies in the fact that the properties of community structure are multivariate and complicated; therefore, it is insufficient to model community structure using a predefined model, the way that is popular in most state-of-the-art network embedding algorithms explicitly considering community structure preservation. In this paper, we introduce a multi-process parallel framework for network embedding that is enhanced by found partial community information and can preserve community properties well. We also implement the framework and propose two node embedding methods that use game theory for detecting partial community information. A series of experiments are conducted to evaluate the performance of our methods and six state-of-the-art algorithms. The results demonstrate that our methods can effectively preserve community properties of networks in their low-dimension representations. Specifically, compared to the involved baselines, our algorithms behave the best and are the runners-up on networks with high overlapping diversity and density.https://www.mdpi.com/2078-2489/12/5/186network representation learningnetwork embeddingpartial community structureego-net analysisgame theorymulti-label classification |
| spellingShingle | Hanlin Sun Wei Jie Jonathan Loo Liang Chen Zhongmin Wang Sugang Ma Gang Li Shuai Zhang Network Representation Learning Enhanced by Partial Community Information That Is Found Using Game Theory Information network representation learning network embedding partial community structure ego-net analysis game theory multi-label classification |
| title | Network Representation Learning Enhanced by Partial Community Information That Is Found Using Game Theory |
| title_full | Network Representation Learning Enhanced by Partial Community Information That Is Found Using Game Theory |
| title_fullStr | Network Representation Learning Enhanced by Partial Community Information That Is Found Using Game Theory |
| title_full_unstemmed | Network Representation Learning Enhanced by Partial Community Information That Is Found Using Game Theory |
| title_short | Network Representation Learning Enhanced by Partial Community Information That Is Found Using Game Theory |
| title_sort | network representation learning enhanced by partial community information that is found using game theory |
| topic | network representation learning network embedding partial community structure ego-net analysis game theory multi-label classification |
| url | https://www.mdpi.com/2078-2489/12/5/186 |
| work_keys_str_mv | AT hanlinsun networkrepresentationlearningenhancedbypartialcommunityinformationthatisfoundusinggametheory AT weijie networkrepresentationlearningenhancedbypartialcommunityinformationthatisfoundusinggametheory AT jonathanloo networkrepresentationlearningenhancedbypartialcommunityinformationthatisfoundusinggametheory AT liangchen networkrepresentationlearningenhancedbypartialcommunityinformationthatisfoundusinggametheory AT zhongminwang networkrepresentationlearningenhancedbypartialcommunityinformationthatisfoundusinggametheory AT sugangma networkrepresentationlearningenhancedbypartialcommunityinformationthatisfoundusinggametheory AT gangli networkrepresentationlearningenhancedbypartialcommunityinformationthatisfoundusinggametheory AT shuaizhang networkrepresentationlearningenhancedbypartialcommunityinformationthatisfoundusinggametheory |