Multiplex network infomax: Multiplex network embedding via information fusion
For networking of big data applications, an essential issue is how to represent networks in vector space for further mining and analysis tasks, e.g., node classification, clustering, link prediction, and visualization. Most existing studies on this subject mainly concentrate on monoplex networks con...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2023-10-01
|
| Series: | Digital Communications and Networks |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352864822002115 |
| _version_ | 1827773828612227072 |
|---|---|
| author | Qiang Wang Hao Jiang Ying Jiang Shuwen Yi Qi Nie Geng Zhang |
| author_facet | Qiang Wang Hao Jiang Ying Jiang Shuwen Yi Qi Nie Geng Zhang |
| author_sort | Qiang Wang |
| collection | DOAJ |
| description | For networking of big data applications, an essential issue is how to represent networks in vector space for further mining and analysis tasks, e.g., node classification, clustering, link prediction, and visualization. Most existing studies on this subject mainly concentrate on monoplex networks considering a single type of relation among nodes. However, numerous real-world networks are naturally composed of multiple layers with different relation types; such a network is called a multiplex network. The majority of existing multiplex network embedding methods either overlook node attributes, resort to node labels for training, or underutilize underlying information shared across multiple layers. In this paper, we propose Multiplex Network Infomax (MNI), an unsupervised embedding framework to represent information of multiple layers into a unified embedding space. To be more specific, we aim to maximize the mutual information between the unified embedding and node embeddings of each layer. On the basis of this framework, we present an unsupervised network embedding method for attributed multiplex networks. Experimental results show that our method achieves competitive performance on not only node-related tasks, such as node classification, clustering, and similarity search, but also a typical edge-related task, i.e., link prediction, at times even outperforming relevant supervised methods, despite that MNI is fully unsupervised. |
| first_indexed | 2024-03-11T13:29:19Z |
| format | Article |
| id | doaj.art-405c4fee1d294ec1934c39bc61659d26 |
| institution | Directory Open Access Journal |
| issn | 2352-8648 |
| language | English |
| last_indexed | 2024-03-11T13:29:19Z |
| publishDate | 2023-10-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Digital Communications and Networks |
| spelling | doaj.art-405c4fee1d294ec1934c39bc61659d262023-11-03T04:15:11ZengKeAi Communications Co., Ltd.Digital Communications and Networks2352-86482023-10-019511571168Multiplex network infomax: Multiplex network embedding via information fusionQiang Wang0Hao Jiang1Ying Jiang2Shuwen Yi3Qi Nie4Geng Zhang5Electronic Information School, Wuhan University, Wuhan, 430072, ChinaElectronic Information School, Wuhan University, Wuhan, 430072, China; Corresponding author.School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, 510006, ChinaElectronic Information School, Wuhan University, Wuhan, 430072, ChinaElectronic Information School, Wuhan University, Wuhan, 430072, ChinaElectronic Information School, Wuhan University, Wuhan, 430072, China; China Electric Power Research Institute, Beijing, 100192, ChinaFor networking of big data applications, an essential issue is how to represent networks in vector space for further mining and analysis tasks, e.g., node classification, clustering, link prediction, and visualization. Most existing studies on this subject mainly concentrate on monoplex networks considering a single type of relation among nodes. However, numerous real-world networks are naturally composed of multiple layers with different relation types; such a network is called a multiplex network. The majority of existing multiplex network embedding methods either overlook node attributes, resort to node labels for training, or underutilize underlying information shared across multiple layers. In this paper, we propose Multiplex Network Infomax (MNI), an unsupervised embedding framework to represent information of multiple layers into a unified embedding space. To be more specific, we aim to maximize the mutual information between the unified embedding and node embeddings of each layer. On the basis of this framework, we present an unsupervised network embedding method for attributed multiplex networks. Experimental results show that our method achieves competitive performance on not only node-related tasks, such as node classification, clustering, and similarity search, but also a typical edge-related task, i.e., link prediction, at times even outperforming relevant supervised methods, despite that MNI is fully unsupervised.http://www.sciencedirect.com/science/article/pii/S2352864822002115Network embeddingMultiplex networkMutual information maximization |
| spellingShingle | Qiang Wang Hao Jiang Ying Jiang Shuwen Yi Qi Nie Geng Zhang Multiplex network infomax: Multiplex network embedding via information fusion Digital Communications and Networks Network embedding Multiplex network Mutual information maximization |
| title | Multiplex network infomax: Multiplex network embedding via information fusion |
| title_full | Multiplex network infomax: Multiplex network embedding via information fusion |
| title_fullStr | Multiplex network infomax: Multiplex network embedding via information fusion |
| title_full_unstemmed | Multiplex network infomax: Multiplex network embedding via information fusion |
| title_short | Multiplex network infomax: Multiplex network embedding via information fusion |
| title_sort | multiplex network infomax multiplex network embedding via information fusion |
| topic | Network embedding Multiplex network Mutual information maximization |
| url | http://www.sciencedirect.com/science/article/pii/S2352864822002115 |
| work_keys_str_mv | AT qiangwang multiplexnetworkinfomaxmultiplexnetworkembeddingviainformationfusion AT haojiang multiplexnetworkinfomaxmultiplexnetworkembeddingviainformationfusion AT yingjiang multiplexnetworkinfomaxmultiplexnetworkembeddingviainformationfusion AT shuwenyi multiplexnetworkinfomaxmultiplexnetworkembeddingviainformationfusion AT qinie multiplexnetworkinfomaxmultiplexnetworkembeddingviainformationfusion AT gengzhang multiplexnetworkinfomaxmultiplexnetworkembeddingviainformationfusion |