DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 황성주 | - |
dc.contributor.author | Kim, Dongki | - |
dc.contributor.author | 김동기 | - |
dc.date.accessioned | 2024-07-25T19:30:43Z | - |
dc.date.available | 2024-07-25T19:30:43Z | - |
dc.date.issued | 2023 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1045712&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/320524 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 김재철AI대학원, 2023.8,[iv, 60 p. :] | - |
dc.description.abstract | The structural characteristics of a graph, such as connectivity, are important factors that determine its properties. My thesis focuses on self-supervised learning methods and generative models to explicitly learn the structural characteristics of graphs. Firstly, we propose a self-supervised learning method that can discretize the embedding space depending on the discrete graph structure. The proposed method enables the discrimination between valid and invalid graphs and explicitly learns the differences in graph connectivity. Through experiments, we demonstrated that even small differences can be distinguished clearly, unlike traditional contrastive learning techniques. Secondly, we proposed a generative model that explicitly models the characteristics of graphs when generating the graphs. To this end, we derive a destination-driven generation process and proposed a new objective function that predicts the destination of the generation process. The proposed method allows the generation of graphs with inherent properties and demonstrated the generation of valid graphs. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 그래프 자가지도학습법▼a그래프 생성모델▼a그래프 신경망 | - |
dc.subject | Graph self-supervised learning▼aGraph generative model▼aGraph neural network | - |
dc.title | Graph self-supervised learning and generative model for modeling graph structural property | - |
dc.title.alternative | 그래프 구조적 특성 모델링을 위한 자가지도학습법 및 생성모델 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :김재철AI대학원, | - |
dc.contributor.alternativeauthor | Hwang, Sung Ju | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.