Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Yi, Eunjeong | - |
dc.contributor.author | Kim, Min-Soo | - |
dc.date.accessioned | 2023-12-26T18:13:42Z | - |
dc.date.available | 2023-12-26T18:13:42Z | - |
dc.date.created | 2022-01-07 | - |
dc.date.issued | 2022-05-18 | - |
dc.identifier.isbn | 9783030922306 | - |
dc.identifier.issn | 1865-0929 | - |
dc.identifier.uri | http://hdl.handle.net/20.500.11750/46848 | - |
dc.description.abstract | Recently, graph neural networks (GNNs) have been improved under the influence of various deep learning techniques, such as attention, autoencoders, and recurrent networks. However, real-world graphs may have multiple types of vertices and edges, such as graphs of social networks, citation networks, and e-commerce data. In these cases, most GNNs that consider a homogeneous graph as input data are not suitable because they ignore the heterogeneity. Meta-path-based methods have been researched to capture both heterogeneity and structural information of heterogeneous graphs. As a meta-path is a type of graph pattern, we extend the use of meta-paths to exploit graph patterns. In this study, we propose TP-HAN, a heterogeneous graph attention network for exploiting triangle patterns. In the experiments using DBLP and IMDB, we show that TP-HAN outperforms the state-of-the-art heterogeneous graph attention network. © 2022, Springer Nature Switzerland AG. | - |
dc.language | English | - |
dc.publisher | Research Center for Big data Edge Cloud Services (BECS, KAIST) | - |
dc.relation.ispartof | Communications in Computer and Information Science | - |
dc.title | Exploiting Triangle Patterns for Heterogeneous Graph Attention Network | - |
dc.type | Conference Paper | - |
dc.identifier.doi | 10.1007/978-3-030-92231-3_7 | - |
dc.identifier.wosid | 000927881600007 | - |
dc.identifier.scopusid | 2-s2.0-85121908542 | - |
dc.identifier.bibliographicCitation | 1st International Workshop on Big data-driven Edge Cloud Services, BECS 2021, pp.71 - 81 | - |
dc.identifier.url | https://becs.kaist.ac.kr/iwbecs2021/ | - |
dc.citation.conferenceDate | 2021-05-18 | - |
dc.citation.conferencePlace | FR | - |
dc.citation.conferencePlace | Virtual | - |
dc.citation.endPage | 81 | - |
dc.citation.startPage | 71 | - |
dc.citation.title | 1st International Workshop on Big data-driven Edge Cloud Services, BECS 2021 | - |
There are no files associated with this item.