Self-supervised community detection in multiplex networks with graph convolutional autoencoder
Community detection in multiplex networks has received considerable attention in recent years. However, existing methods that combine graph embedding and downstream tasks still face two challenges. The first is how to fully explore the correlation among the layers in the multiplex networks, and the...
Uloženo v:
| Vydáno v: | Proceedings of the ... International Conference on Computer Supported Cooperative Work in Design (Online) s. 1378 - 1383 |
|---|---|
| Hlavní autoři: | , , , , , |
| Médium: | Konferenční příspěvek |
| Jazyk: | angličtina |
| Vydáno: |
IEEE
24.05.2023
|
| Témata: | |
| ISSN: | 2768-1904 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Community detection in multiplex networks has received considerable attention in recent years. However, existing methods that combine graph embedding and downstream tasks still face two challenges. The first is how to fully explore the correlation among the layers in the multiplex networks, and the second is how to make the learned node representation more applicable to the community detection tasks. Aiming at these challenges, we propose a novel self-supervised multiplex community detection model called MGCAE which is based on graph neural networks. To solve the first challenge, we compute the mutual information maximization loss in the self-supervision module. The mutual information includes global representation and common representation of nodes in different layers, and node representation in each layer. For the second challenge, we combine a Bernoulli-Poisson loss and a modularity maximization loss to jointly optimize the reconstruction of the original adjacency matrix, which is in line with the rigorous theory of modularity. We treat graph convolutional autoencoder (GCAE) as the backbone framework and train it by using the unified loss mentioned above. In addition, the model obtains the community detection results in an end-to-end manner, which makes the model independent of downstream tasks and more stable. Experiments on real-world attributed multiplex network datasets demonstrate the effectiveness of our model. |
|---|---|
| AbstractList | Community detection in multiplex networks has received considerable attention in recent years. However, existing methods that combine graph embedding and downstream tasks still face two challenges. The first is how to fully explore the correlation among the layers in the multiplex networks, and the second is how to make the learned node representation more applicable to the community detection tasks. Aiming at these challenges, we propose a novel self-supervised multiplex community detection model called MGCAE which is based on graph neural networks. To solve the first challenge, we compute the mutual information maximization loss in the self-supervision module. The mutual information includes global representation and common representation of nodes in different layers, and node representation in each layer. For the second challenge, we combine a Bernoulli-Poisson loss and a modularity maximization loss to jointly optimize the reconstruction of the original adjacency matrix, which is in line with the rigorous theory of modularity. We treat graph convolutional autoencoder (GCAE) as the backbone framework and train it by using the unified loss mentioned above. In addition, the model obtains the community detection results in an end-to-end manner, which makes the model independent of downstream tasks and more stable. Experiments on real-world attributed multiplex network datasets demonstrate the effectiveness of our model. |
| Author | Cheng, Junwei Cheng, Hao Liu, Xingyu Guan, Quanlong Chen, Qimai He, Chaobo |
| Author_xml | – sequence: 1 givenname: Xingyu surname: Liu fullname: Liu, Xingyu email: jung@m.scnu.edu.cn organization: South China Normal University,School of Computer Science,Guangzhou,China,510631 – sequence: 2 givenname: Junwei surname: Cheng fullname: Cheng, Junwei email: liuxingyu@m.scnu.edu.cn organization: South China Normal University,School of Computer Science,Guangzhou,China,510631 – sequence: 3 givenname: Hao surname: Cheng fullname: Cheng, Hao email: haocheng@m.scnu.edu.cn organization: South China Normal University,School of Computer Science,Guangzhou,China,510631 – sequence: 4 givenname: Chaobo surname: He fullname: He, Chaobo email: hechaobo@foxmail.com organization: South China Normal University,School of Computer Science,Guangzhou,China,510631 – sequence: 5 givenname: Qimai surname: Chen fullname: Chen, Qimai email: chenqimai@scnu.edu.cn organization: South China Normal University,School of Computer Science,Guangzhou,China,510631 – sequence: 6 givenname: Quanlong surname: Guan fullname: Guan, Quanlong email: gql@jnu.edu.cn organization: Jinan University,College of Information Science and Technology,GuangZhou,China,510631 |
| BookMark | eNo1kMtOwzAUBQ0CiVL6Byz8AynXduLHEoWnVIlFQeyonPiaGhInShxK_x4QsDqbmVmcU3IUu4iEUAZLxsBclOvy-apQuYQlBy6WDFjBpVIHZGGU0aIAIZjU-SGZcSV1xgzkJ2Qxjm8AIDhj0qgZeVlj47Nx6nH4CCM6WndtO8WQ9tRhwjqFLtIQaTs1KfQNftKIadcN7yPdhbSlr4Ptt99S_Oia6Qe2DbVT6jDWncPhjBx724y4-Ns5ebq5fizvstXD7X15ucoCYyZlhkNVgOROOqG9cLXSHHJXVUJbzyow4LQWSlqDsjYavAIvbaFzX3GvKyXm5Py3GxBx0w-htcN-83-J-AL9tVp4 |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IL CBEJK RIE RIL |
| DOI | 10.1109/CSCWD57460.2023.10152677 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE Xplore Digital Library IEEE Proceedings Order Plans (POP All) 1998-Present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISBN | 9798350331684 |
| EISSN | 2768-1904 |
| EndPage | 1383 |
| ExternalDocumentID | 10152677 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: National Natural Science Foundation of China funderid: 10.13039/501100001809 – fundername: Ministry of Education funderid: 10.13039/100009950 – fundername: Natural Science Foundation of Guangdong Province funderid: 10.13039/501100003453 |
| GroupedDBID | 6IE 6IL 6IN AAWTH ABLEC ADZIZ ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK CHZPO IEGSK OCL RIE RIL |
| ID | FETCH-LOGICAL-i119t-920b5062d6d38f3dc78204dbb38af1b090d88376a9e6c980f70f6a584fb2f8b73 |
| IEDL.DBID | RIE |
| IngestDate | Wed Aug 27 02:51:04 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | false |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-i119t-920b5062d6d38f3dc78204dbb38af1b090d88376a9e6c980f70f6a584fb2f8b73 |
| PageCount | 6 |
| ParticipantIDs | ieee_primary_10152677 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-May-24 |
| PublicationDateYYYYMMDD | 2023-05-24 |
| PublicationDate_xml | – month: 05 year: 2023 text: 2023-May-24 day: 24 |
| PublicationDecade | 2020 |
| PublicationTitle | Proceedings of the ... International Conference on Computer Supported Cooperative Work in Design (Online) |
| PublicationTitleAbbrev | CSCWD |
| PublicationYear | 2023 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| SSID | ssj0003211697 |
| Score | 1.8327781 |
| Snippet | Community detection in multiplex networks has received considerable attention in recent years. However, existing methods that combine graph embedding and... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 1378 |
| SubjectTerms | Community detection Computational modeling Correlation Federated learning Graph convolutional autoencoder Graph neural networks Multiplex networks Multiplexing Mutual information Self-supervised learning Task analysis |
| Title | Self-supervised community detection in multiplex networks with graph convolutional autoencoder |
| URI | https://ieeexplore.ieee.org/document/10152677 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA62eNCLr4pvcvCamt1k8zhXxVMpVLEnS55QKNvS7or-e5Nst-rBg7cQEghJhplMvu8bAG5ViPGVzjzynheI5k4hkdMChcibMmIJtUanYhN8OBSTiRxtyOqJC-OcS-Az14_N9JdvF6aOqbJg4cHbMM47oMM5a8ha24QKCU8ZJnmL1sHybjAevN4XnDLcj0XC--30X4VUkh95PPjnCg5B75uRB0dbX3MEdlx5DPZ_iAmegLexm3u0rpfR-tfOQtNwP6pPaF2VEFclnJWwhRB-wLKBgK9hTMbCJF0NIwp9cxvVHKq6WkSlS-tWPfDy-PA8eEKb6glolmWyQjLHusAst8wS4Yk1URmPWq2JUD7TWGIrwuuUKemYkQJ7jj1TIR7xOvdCc3IKuuWidGcARrIqF1QK6jxVGdFhYK485joEM8bIc9CLWzVdNgIZ03aXLv7ovwR78UDiJ3xOr0C3WtXuGuya92q2Xt2kY_0C4gulgg |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5aBfXiq-LbHLymZnezeZyrpWIthVbsyZJsEiiUbenuiv57k91u1YMHbyGEEJIMM5l83zcA3EoX40sVWGQtixEJjUQ8JDFykTehkY6ITlRZbIL1-3w8FoMVWb3kwhhjSvCZaflm-Zev50nhU2XOwp23oYxtgq2YkBBXdK11SiVyjxkqWI3XweKuPWy_3seMUNzyZcJb9QS_SqmUnqSz_881HIDmNycPDtbe5hBsmPQI7P2QEzwGb0MzsygrFt7-M6NhUrE_8k-oTV5irlI4TWENIvyAaQUCz6BPx8JSvBp6HPrqPsoZlEU-91qX2iyb4KXzMGp30ap-ApoGgciRCLGKMQ011RG3kU68Nh7RSkVc2kBhgTV371MqhaGJ4NgybKl0EYlVoeWKRSegkc5Tcwqgp6syTgQnxhIZRMoNDKXFTLlwJknEGWj6rZosKomMSb1L53_034Cd7ui5N-k99p8uwK4_HP8lH5JL0MiXhbkC28l7Ps2W1-URfwGqBajJ |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=Proceedings+of+the+...+International+Conference+on+Computer+Supported+Cooperative+Work+in+Design+%28Online%29&rft.atitle=Self-supervised+community+detection+in+multiplex+networks+with+graph+convolutional+autoencoder&rft.au=Liu%2C+Xingyu&rft.au=Cheng%2C+Junwei&rft.au=Cheng%2C+Hao&rft.au=He%2C+Chaobo&rft.date=2023-05-24&rft.pub=IEEE&rft.eissn=2768-1904&rft.spage=1378&rft.epage=1383&rft_id=info:doi/10.1109%2FCSCWD57460.2023.10152677&rft.externalDocID=10152677 |