File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1145/3442381.3449821
- Scopus: eid_2-s2.0-85107940011
- WOS: WOS:000733621801056
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: Motif-preserving dynamic attributed network embedding
Title | Motif-preserving dynamic attributed network embedding |
---|---|
Authors | |
Keywords | Dynamic networks Graph neural networks Network embedding |
Issue Date | 2021 |
Citation | The Web Conference 2021 - Proceedings of the World Wide Web Conference, WWW 2021, 2021, p. 1629-1638 How to Cite? |
Abstract | Network embedding has emerged as a new learning paradigm to embed complex network into a low-dimensional vector space while preserving node proximities in both network structures and properties. It advances various network mining tasks, ranging from link prediction to node classification. However, most existing works primarily focus on static networks while many networks in real-life evolve over time with addition/deletion of links and nodes, naturally with associated attribute evolution. In this work, we present Motif-preserving Temporal Shift Network (MTSN), a novel dynamic network embedding framework that simultaneously models the local high-order structures and temporal evolution for dynamic attributed networks. Specifically, MTSN learns node representations by stacking the proposed TIME module to capture both local high-order structural proximities and node attributes by motif-preserving encoder and temporal dynamics by temporal shift operation in a dynamic attributed network. Finally, we perform extensive experiments on four real-world network datasets to demonstrate the superiority of MTSN against state-of-the-art network embedding baselines in terms of both effectiveness and efficiency. The source code of our method is available at: https://github.com/ZhijunLiu95/MTSN. |
Persistent Identifier | http://hdl.handle.net/10722/308871 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Liu, Zhijun | - |
dc.contributor.author | Huang, Chao | - |
dc.contributor.author | Yu, Yanwei | - |
dc.contributor.author | Dong, Junyu | - |
dc.date.accessioned | 2021-12-08T07:50:18Z | - |
dc.date.available | 2021-12-08T07:50:18Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | The Web Conference 2021 - Proceedings of the World Wide Web Conference, WWW 2021, 2021, p. 1629-1638 | - |
dc.identifier.uri | http://hdl.handle.net/10722/308871 | - |
dc.description.abstract | Network embedding has emerged as a new learning paradigm to embed complex network into a low-dimensional vector space while preserving node proximities in both network structures and properties. It advances various network mining tasks, ranging from link prediction to node classification. However, most existing works primarily focus on static networks while many networks in real-life evolve over time with addition/deletion of links and nodes, naturally with associated attribute evolution. In this work, we present Motif-preserving Temporal Shift Network (MTSN), a novel dynamic network embedding framework that simultaneously models the local high-order structures and temporal evolution for dynamic attributed networks. Specifically, MTSN learns node representations by stacking the proposed TIME module to capture both local high-order structural proximities and node attributes by motif-preserving encoder and temporal dynamics by temporal shift operation in a dynamic attributed network. Finally, we perform extensive experiments on four real-world network datasets to demonstrate the superiority of MTSN against state-of-the-art network embedding baselines in terms of both effectiveness and efficiency. The source code of our method is available at: https://github.com/ZhijunLiu95/MTSN. | - |
dc.language | eng | - |
dc.relation.ispartof | The Web Conference 2021 - Proceedings of the World Wide Web Conference, WWW 2021 | - |
dc.subject | Dynamic networks | - |
dc.subject | Graph neural networks | - |
dc.subject | Network embedding | - |
dc.title | Motif-preserving dynamic attributed network embedding | - |
dc.type | Conference_Paper | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1145/3442381.3449821 | - |
dc.identifier.scopus | eid_2-s2.0-85107940011 | - |
dc.identifier.spage | 1629 | - |
dc.identifier.epage | 1638 | - |
dc.identifier.isi | WOS:000733621801056 | - |