DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Hwang, Sung Ju | - |
dc.contributor.advisor | 황성주 | - |
dc.contributor.author | Shin, Jae Woong | - |
dc.date.accessioned | 2022-04-15T07:56:33Z | - |
dc.date.available | 2022-04-15T07:56:33Z | - |
dc.date.issued | 2021 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=963741&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/294849 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : AI대학원, 2021.8,[iv, 31 p. :] | - |
dc.description.abstract | Meta-learning of shared initialization parameters has shown to be highly effective in solving few-shot learning tasks. However, extending the framework to many-shot scenarios, which may further enhance its practicality, has been relatively overlooked due to the technical difficulties of meta-learning over long chains of inner-gradient steps. In this paper, we first show that allowing the meta-learners to take a larger number of inner gradient steps better captures the structure of heterogeneous and large-scale task distributions, thus results in obtaining better initialization points. Further, in order to increase the frequency of meta-updates even with the excessively long inner-optimization trajectories, we propose to estimate the $\emph{required shift}$ of the task-specific parameters with respect to the change of the initialization parameters. By doing so, we can arbitrarily increase the frequency of meta-updates and thus greatly improve the meta-level convergence as well as the quality of the learned initializations. We validate our method on a heterogeneous set of large-scale tasks and show that the algorithm largely outperforms the previous first-order meta-learning methods in terms of both generalization performance and convergence, as well as multi-task learning and fine-tuning baselines. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Meta learning▼aLarge scale | - |
dc.subject | 메타 러닝▼a대규모 학습 | - |
dc.title | Large-scale meta-learning with continual trajectory shifting | - |
dc.title.alternative | 연속적 경로 이동을 통한 대규모 메타러닝 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :AI대학원, | - |
dc.contributor.alternativeauthor | 신재웅 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.