Semi-supervised community detection method based on generative adversarial networks
Community detection in complex networks often suffers from insufficient data and limited utilization of prior knowledge. In this paper we propose “Semi-supervised Generative Adversarial Network” (GANSE), a novel algorithm that integrates Generative Adversarial Networks (GANs) and semi-supervised lea...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-03-01
|
| Series: | Journal of King Saud University: Computer and Information Sciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1319157824000971 |
| _version_ | 1827314740201783296 |
|---|---|
| author | Xiaoyang Liu Mengyao Zhang Yanfei Liu Chao Liu Chaorong Li Wei Wang Xiaoqin Zhang Asgarali Bouyer |
| author_facet | Xiaoyang Liu Mengyao Zhang Yanfei Liu Chao Liu Chaorong Li Wei Wang Xiaoqin Zhang Asgarali Bouyer |
| author_sort | Xiaoyang Liu |
| collection | DOAJ |
| description | Community detection in complex networks often suffers from insufficient data and limited utilization of prior knowledge. In this paper we propose “Semi-supervised Generative Adversarial Network” (GANSE), a novel algorithm that integrates Generative Adversarial Networks (GANs) and semi-supervised learning to address these challenges. This method addresses the issues above through a multi-step process. Initially, the network is rewired using vertex similarity metrics, thereby enhancing its structural integrity. Subsequently, a novel generative adversarial network model is designed, and our model facilitates the reconstruction of the network, thereby yielding partitions. Which form the basis for identifying core communities. Additionally, the local clustering coefficient is incorporated as a reward signal and injected into the node selection process. Moreover, isolated nodes are reallocated, ultimately culminating in the derivation of the final community structure. Experimental results on four large real-life datasets demonstrate the clear superiority of the proposed algorithm in terms of F1 and Jaccard metrics when compared to existing algorithms. Notably, our GANSE method outperforms the traditional algorithms in networks with “missing data”. Thus showing its robustness and effectiveness in real-world incomplete datasets. Our findings highlight the potential of GANs and semi-supervised learning for enhancing community detection accuracy in complex networks. |
| first_indexed | 2024-04-24T22:41:24Z |
| format | Article |
| id | doaj.art-4d72fe40f08249c9a2c7413bc3694d3c |
| institution | Directory Open Access Journal |
| issn | 1319-1578 |
| language | English |
| last_indexed | 2024-04-24T22:41:24Z |
| publishDate | 2024-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of King Saud University: Computer and Information Sciences |
| spelling | doaj.art-4d72fe40f08249c9a2c7413bc3694d3c2024-03-19T04:18:20ZengElsevierJournal of King Saud University: Computer and Information Sciences1319-15782024-03-01363102008Semi-supervised community detection method based on generative adversarial networksXiaoyang Liu0Mengyao Zhang1Yanfei Liu2Chao Liu3Chaorong Li4Wei Wang5Xiaoqin Zhang6Asgarali Bouyer7Chongqing University of Technology, Chongqing, China; Corresponding author.School of Artificial Intelligence and Big Data, Chongqing Metropolitan College of Science and Technology, Chongqing 402160, ChinaCollege of Intelligence and Computing, Tianjin University, Tianjin 300000, ChinaChongqing University of Technology, Chongqing, ChinaChongqing University of Technology, Chongqing, ChinaSchool of Public Health, Chongqing Medical University, Chongqing 400016, ChinaChongqing Communication Design Institute Co.Ltd., Chongqing 400041, ChinaFaculty of Computer Engineering and Information Technology, Azarbaijan Shahid Madani University, Tabriz, Iran; Department of Software Engineering, Faculty of Engineering and Natural Science, Istinye University, Istanbul, TurkeyCommunity detection in complex networks often suffers from insufficient data and limited utilization of prior knowledge. In this paper we propose “Semi-supervised Generative Adversarial Network” (GANSE), a novel algorithm that integrates Generative Adversarial Networks (GANs) and semi-supervised learning to address these challenges. This method addresses the issues above through a multi-step process. Initially, the network is rewired using vertex similarity metrics, thereby enhancing its structural integrity. Subsequently, a novel generative adversarial network model is designed, and our model facilitates the reconstruction of the network, thereby yielding partitions. Which form the basis for identifying core communities. Additionally, the local clustering coefficient is incorporated as a reward signal and injected into the node selection process. Moreover, isolated nodes are reallocated, ultimately culminating in the derivation of the final community structure. Experimental results on four large real-life datasets demonstrate the clear superiority of the proposed algorithm in terms of F1 and Jaccard metrics when compared to existing algorithms. Notably, our GANSE method outperforms the traditional algorithms in networks with “missing data”. Thus showing its robustness and effectiveness in real-world incomplete datasets. Our findings highlight the potential of GANs and semi-supervised learning for enhancing community detection accuracy in complex networks.http://www.sciencedirect.com/science/article/pii/S1319157824000971Generative adversarial networksCommunity detectionSemi-unsupervised learningComplex networks |
| spellingShingle | Xiaoyang Liu Mengyao Zhang Yanfei Liu Chao Liu Chaorong Li Wei Wang Xiaoqin Zhang Asgarali Bouyer Semi-supervised community detection method based on generative adversarial networks Journal of King Saud University: Computer and Information Sciences Generative adversarial networks Community detection Semi-unsupervised learning Complex networks |
| title | Semi-supervised community detection method based on generative adversarial networks |
| title_full | Semi-supervised community detection method based on generative adversarial networks |
| title_fullStr | Semi-supervised community detection method based on generative adversarial networks |
| title_full_unstemmed | Semi-supervised community detection method based on generative adversarial networks |
| title_short | Semi-supervised community detection method based on generative adversarial networks |
| title_sort | semi supervised community detection method based on generative adversarial networks |
| topic | Generative adversarial networks Community detection Semi-unsupervised learning Complex networks |
| url | http://www.sciencedirect.com/science/article/pii/S1319157824000971 |
| work_keys_str_mv | AT xiaoyangliu semisupervisedcommunitydetectionmethodbasedongenerativeadversarialnetworks AT mengyaozhang semisupervisedcommunitydetectionmethodbasedongenerativeadversarialnetworks AT yanfeiliu semisupervisedcommunitydetectionmethodbasedongenerativeadversarialnetworks AT chaoliu semisupervisedcommunitydetectionmethodbasedongenerativeadversarialnetworks AT chaorongli semisupervisedcommunitydetectionmethodbasedongenerativeadversarialnetworks AT weiwang semisupervisedcommunitydetectionmethodbasedongenerativeadversarialnetworks AT xiaoqinzhang semisupervisedcommunitydetectionmethodbasedongenerativeadversarialnetworks AT asgaralibouyer semisupervisedcommunitydetectionmethodbasedongenerativeadversarialnetworks |