Publications
Detailed Information
Low-Rank Matrix Completion Using Graph Neural Network
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Luong Trung Nguyen | - |
dc.contributor.author | Shim, Byonghyo | - |
dc.date.accessioned | 2022-10-17T04:27:49Z | - |
dc.date.available | 2022-10-17T04:27:49Z | - |
dc.date.created | 2022-10-06 | - |
dc.date.issued | 2020-10 | - |
dc.identifier.citation | 11TH INTERNATIONAL CONFERENCE ON ICT CONVERGENCE: DATA, NETWORK, AND AI IN THE AGE OF UNTACT (ICTC 2020), pp.17-21 | - |
dc.identifier.issn | 2162-1233 | - |
dc.identifier.uri | https://hdl.handle.net/10371/186301 | - |
dc.description.abstract | In this paper, we propose the graph neural network (GNN)-based matrix completion technique to reconstruct the desired low-rank matrix by exploiting the underlying graph structure of the matrix. The proposed approach, referred to as GNN-based low-rank matrix completion (GNN-LRMC), combines the GNN and the neural-network weight update mechanism. The GNN is used to extract the node vectors of the graph using a modified convolution operation. Empirical simulations validate the reconstruction performance of GNN-LRMC in synthetic and Netflix datasets. | - |
dc.language | 영어 | - |
dc.publisher | IEEE | - |
dc.title | Low-Rank Matrix Completion Using Graph Neural Network | - |
dc.type | Article | - |
dc.identifier.doi | 10.1109/ICTC49870.2020.9289469 | - |
dc.citation.journaltitle | 11TH INTERNATIONAL CONFERENCE ON ICT CONVERGENCE: DATA, NETWORK, AND AI IN THE AGE OF UNTACT (ICTC 2020) | - |
dc.identifier.wosid | 000692529100004 | - |
dc.identifier.scopusid | 2-s2.0-85099004655 | - |
dc.citation.endpage | 21 | - |
dc.citation.startpage | 17 | - |
dc.description.isOpenAccess | N | - |
dc.contributor.affiliatedAuthor | Shim, Byonghyo | - |
dc.type.docType | Proceedings Paper | - |
dc.description.journalClass | 1 | - |
- Appears in Collections:
- Files in This Item:
- There are no files associated with this item.
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.