DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Lee, Juho | - |
dc.contributor.advisor | 이주호 | - |
dc.contributor.author | Kim, Hyun Mog | - |
dc.date.accessioned | 2023-06-22T19:31:19Z | - |
dc.date.available | 2023-06-22T19:31:19Z | - |
dc.date.issued | 2023 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1032314&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/308201 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 김재철AI대학원, 2023.2,[iv, 38 p. :] | - |
dc.description.abstract | Graph Neural Networks (GNN) have been proven effective in non-euclidean data such as social networks, biology networks, and chemistry networks. There are various ways to further improve network performance. Numerous papers have found that enlarging model size is not a viable solution in improving the model’s performance due to over-smoothing. Feasible methods to improve performance were therefore considered, with the Ensemble method put forth as the most appropriate approach. We therefore decided to conduct experiments using the Ensemble method, and as an extension, applied BatchEnsemble, an Ensemble method of greater efficiency, to graph-structured datasets and neural networks to observe its effectiveness in such contexts. In this paper, BatchEnsemble is proven to achieve better performance than the Ensemble with GNNs. For credibility, we tested the performance of both Ensemble and BatchEnsemble on node classification (Cora, CiteSeer, and PubMed) and graph classification tasks (MUTAG, PROTEINS, and COLLAB) using three iconic GNNs: Graph Convolutional Network, Graph Isomorphism Network, and Graph Attention Network. The BatchEnsemble yielded better accuracy and uncertainty measures than the Ensemble method on both node and graph classification tasks | - |
dc.description.abstract | both training and inference times were faster in the BatchEnsemble setting. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Ensemble▼aBatchEnsemble▼aGraph neural networks | - |
dc.subject | 앙상블▼a배치앙상블▼a그래프 신경망 | - |
dc.title | Efficient ensemble for graph neural networks | - |
dc.title.alternative | 그래프 신경망을 위한 효율적인 앙상블 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :김재철AI대학원, | - |
dc.contributor.alternativeauthor | 김현목 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.