DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 신진우 | - |
dc.contributor.author | Nam, Jaehyun | - |
dc.contributor.author | 남재현 | - |
dc.date.accessioned | 2024-07-25T19:30:49Z | - |
dc.date.available | 2024-07-25T19:30:49Z | - |
dc.date.issued | 2023 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1045743&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/320555 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 김재철AI대학원, 2023.8,[iii, 19 p. :] | - |
dc.description.abstract | Learning with few labeled tabular samples is often an essential requirement for industrial machine learning applications as varieties of tabular data suffer from high annotation costs or have difficulties in collecting new samples for novel tasks. Despite the utter importance, such a problem is quite under-explored in the field of tabular learning, and existing few-shot learning schemes from other domains are not straightforward to apply, mainly due to the heterogeneous characteristics of tabular data. In this paper, we propose a simple yet effective framework for few-shot semi-supervised tabular learning, coined Self- generated Tasks from UNlabeled Tables (STUNT). Our key idea is to self-generate diverse few-shot tasks by treating randomly chosen columns as a target label. We then employ a meta-learning scheme to learn generalizable knowledge with the constructed tasks. Moreover, we introduce an unsupervised validation scheme for hyperparameter search (and early stopping) by generating a pseudo-validation set using STUNT from unlabeled data. Our experimental results demonstrate that our simple framework brings significant performance gain under various tabular few-shot learning benchmarks, compared to prior semi- and self-supervised baselines. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 표 형식 데이터▼a극단적 준지도 학습▼a비지도 메타학습 | - |
dc.subject | Tabular representation learning▼aFew-shot semi-supervised learning▼aUnsupervised meta-learning | - |
dc.title | STUNT: few-shot tabular learning with self-generated tasks from unlabeled tables | - |
dc.title.alternative | 비지도 메타학습 방법론을 통한 표 형식 데이터에서의 극단적 준지도 학습 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :김재철AI대학원, | - |
dc.contributor.alternativeauthor | Shin, Jinwoo | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.