DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Kim, Myoung Ho | - |
dc.contributor.advisor | 김명호 | - |
dc.contributor.author | Kim, Jun Seon | - |
dc.date.accessioned | 2023-06-26T19:31:18Z | - |
dc.date.available | 2023-06-26T19:31:18Z | - |
dc.date.issued | 2023 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1032965&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/309506 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전산학부, 2023.2,[iv, 33 p. :] | - |
dc.description.abstract | Most Knowledge Graph(KG) embedding models require negative sampling to learn the representations of KG by discriminating the differences between positive and negative triples. Knowledge representation learning tasks such as link prediction are heavily influenced by the quality of negative samples. Despite many attempts, generating high-quality negative samples remains a challenge. In this paper, we propose a novel framework, Bootstrapped Knowledge graph Embedding based on Neighbor Expansion (BKENE), which learns representations of KG without using negative samples. Our model avoids using augmentation methods that can alter the semantic information when creating the two semantically similar views of KG. In particular, we generate an alternative view of KG by aggregating the information of the expanded neighbor of each node with multi-hop relation. Experimental results show that our BKENE outperforms the state-of-the-art methods for link prediction tasks. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Knowledge Graph Embedding▼aGraph Embedding▼aGraph Neural Networks▼aLink Prediction▼aSelf-Supervised Learning | - |
dc.subject | 지식 그래프 임베딩▼a그래프 임베딩▼a그래프 뉴럴 네트워크▼a링크예측▼a자기지도학습 | - |
dc.title | Link prediction on knowledge graphs based on graph neural networks without negative sampling | - |
dc.title.alternative | 네거티브 샘플링을 하지 않는 그래프 뉴럴 네트워크 기반 지식그래프 링크 예측 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전산학부, | - |
dc.contributor.alternativeauthor | 김준선 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.