DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 박찬영 | - |
dc.contributor.author | Kim, Sungwon | - |
dc.contributor.author | 김성원 | - |
dc.date.accessioned | 2024-07-30T19:30:52Z | - |
dc.date.available | 2024-07-30T19:30:52Z | - |
dc.date.issued | 2024 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1096208&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/321423 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 데이터사이언스대학원, 2024.2,[iv, 31 p. :] | - |
dc.description.abstract | Although Graph Neural Networks (GNNs) have been successful in node classification tasks, their performance heavily relies on the availability of a sufficient number of labeled nodes per class. In real-world situations, not all classes have many labeled nodes and there may be instances where the model needs to classify new classes, making manual labeling difficult. To solve this problem, it is important for GNNs to be able to classify nodes with a limited number of labeled nodes, known as few-shot node classification. Previous episodic meta-learning based methods have demonstrated success in few-shot node classification, but our findings suggest that optimal performance can only be achieved with a substantial amount of diverse training meta-tasks. To address this challenge of meta-learning based few-shot learning (FSL), we propose a new approach, the Task-Equivariant Graph few-shot learning (TEG) framework. Our TEG framework enables the model to learn transferable task-adaptation strategies using a limited number of training meta-tasks, allowing it to acquire meta-knowledge for a wide range of meta-tasks. By incorporating equivariant neural networks, TEG can utilize their strong generalization abilities to learn highly adaptable task-specific strategies. As a result, TEG achieves state-of-the-art performance with limited training meta-tasks. Our experiments on various benchmark datasets demonstrate TEG's superiority in terms of accuracy and generalization ability, even when using minimal meta-training data, highlighting the effectiveness of our proposed approach in addressing the challenges of meta-learning based few-shot node classification. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 노드 분류▼a퓨샷학습▼a그래프 인공신경망▼a등변적 인공신경망 | - |
dc.subject | Node classification▼aFew-shot learning▼aGraph neural networks▼aEquivariant neural networks | - |
dc.title | Task-equivariant graph few-shot learning | - |
dc.title.alternative | 작업-등변성에 기반한 그래프 퓨샷학습 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :데이터사이언스대학원, | - |
dc.contributor.alternativeauthor | Park, Chanyoung | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.