DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 오혜연 | - |
dc.contributor.author | Jin, Jiho | - |
dc.contributor.author | 진지호 | - |
dc.date.accessioned | 2024-07-26T19:31:16Z | - |
dc.date.available | 2024-07-26T19:31:16Z | - |
dc.date.issued | 2022 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1051077&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/321057 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전산학부, 2022.8,[iv, 19 p. :] | - |
dc.description.abstract | Despite the success of Graph Neural Networks (GNNs), they have not been sufficiently addressed from the perspective of transfer learning. Since graphs can attain a variety of structures or features in numerous domains, it is crucial to study the transferability between distinct graphs. In this paper, we explore the node-level transferability of GNNs using synthetic graphs generated by Stochastic Block Model. Our comprehensive experiments on a wide range of synthetic graphs with five GNN models reveal the characteristics of transferability of GNNs, including the influence of the graph structure and the feature information. We also examine the knowledge transfer from synthetic graphs to various real-world graphs. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 그래프 인공 신경망▼a전이 학습▼a스토캐스틱 블록 모델 | - |
dc.subject | Graph neural network▼aTransfer learning▼aStochastic block model | - |
dc.title | Exploring transfer learning of graph neural networks using synthetic graphs | - |
dc.title.alternative | 합성 그래프를 이용한 그래프 인공 신경망의 전이 학습에 대한 탐구 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전산학부, | - |
dc.contributor.alternativeauthor | Oh, Alice | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.