DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Hwang, Sung Ju | - |
dc.contributor.advisor | 황성주 | - |
dc.contributor.author | Na, Donghyun | - |
dc.date.accessioned | 2021-05-11T19:34:25Z | - |
dc.date.available | 2021-05-11T19:34:25Z | - |
dc.date.issued | 2019 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=875478&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/283102 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전산학부, 2019.8,[iii, 17 p. :] | - |
dc.description.abstract | While tasks could come with varying number of instances in realistic settings, the existing meta-learning approaches for few-shot classfication assume even task distributions where the number of instances for each task and class are fixed. Due to such restriction, they learn to equally utilize the meta-knowledge across all the tasks, even when the number of instances per task and class largely varies. Moreover, they do not consider distributional difference in unseen tasks at the meta-test time, on which the meta-knowledge may have varying degree of usefulness depending on the task relatedness. To overcome these limitations, we propose a novel meta-learning model that adaptively balances the effect of the meta-learning and task-specific learning, and also class-specific learning within each task. Through the learning of the balancing variables, we can decide whether to obtain a solution close to the initial parameter or far from it. We formulate this objective into a Bayesian inference framework and solve it using variational inference. Our Bayesian Task-Adaptive Meta-Learning (Bayesian-TAML) significantly outperforms existing meta-learning approaches on benchmark datasets for both few-shot and realistic class- and task-imbalanced datasets, with especially higher gains on the latter. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Meta-learning▼abayeisan▼aimbalanced task▼aout-of-distribution task▼avariational Inference | - |
dc.subject | 메타 학습▼a베이지안▼a불균형 태스크▼a분포 외 태스크▼a변분 추론 | - |
dc.title | Learning to balance | - |
dc.title.alternative | 불균형 및 분포 외 태스크를 고려한 베이지안 메타러닝 방법 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전산학부, | - |
dc.contributor.alternativeauthor | 나동현 | - |
dc.title.subtitle | bayesian meta-learning for imbalanced and out-of-distribution tasks | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.