ShanghaiTech University Knowledge Management System
| TOWARDS FAST ADAPTATION OF NEURAL ARCHITECTURES WITH META LEARNING | |
| 2020 | |
| 会议录名称 | 8TH INTERNATIONAL CONFERENCE ON LEARNING REPRESENTATIONS, ICLR 2020 |
| 发表状态 | 已发表 |
| DOI | 未知 |
| 摘要 | Recently, Neural Architecture Search (NAS) has been successfully applied to multiple artificial intelligence areas and shows better performance compared with hand-designed networks. However, the existing NAS methods only target a specific task. Most of them usually do well in searching an architecture for single task but are troublesome for multiple datasets or multiple tasks. Generally, the architecture for a new task is either searched from scratch, which is neither efficient nor flexible enough for practical application scenarios, or borrowed from the ones searched on other tasks, which might be not optimal. In order to tackle the transferability of NAS and conduct fast adaptation of neural architectures, we propose a novel Transferable Neural Architecture Search method based on meta-learning in this paper, which is termed as T-NAS. T-NAS learns a meta-architecture that is able to adapt to a new task quickly through a few gradient steps, which makes the transferred architecture suitable for the specific task. Extensive experiments show that T-NAS achieves state-of-the-art performance in few-shot learning and comparable performance in supervised learning but with 50x less searching cost, which demonstrates the effectiveness of our method. © 2020 8th International Conference on Learning Representations, ICLR 2020. All rights reserved. |
| 关键词 | Learning systems Application scenario Fast adaptations Learn+ Metalearning Multiple data sets Multiple tasks Neural architectures Performance Search method Specific tasks |
| 会议名称 | 8th International Conference on Learning Representations, ICLR 2020 |
| 会议地点 | Addis Ababa, Ethiopia |
| 会议日期 | April 30, 2020 |
| 收录类别 | EI |
| 语种 | 英语 |
| 出版者 | International Conference on Learning Representations, ICLR |
| EI入藏号 | 20231313796298 |
| EI主题词 | Network architecture |
| 原始文献类型 | Conference article (CA) |
| 文献类型 | 会议论文 |
| 条目标识符 | https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/294853 |
| 专题 | 信息科学与技术学院_博士生 信息科学与技术学院_PI研究组_高盛华组 信息科学与技术学院_本科生 |
| 作者单位 | 1.ShanghaiTech University, China; 2.Weixin Group, Tencent; 3.Tencent AI Lab; 4.University of Texas, Arlington, United States |
| 第一作者单位 | 上海科技大学 |
| 第一作者的第一单位 | 上海科技大学 |
| 推荐引用方式 GB/T 7714 | Lian, Dongze,Zheng, Yin,Xu, Yintao,et al. TOWARDS FAST ADAPTATION OF NEURAL ARCHITECTURES WITH META LEARNING[C]:International Conference on Learning Representations, ICLR,2020. |
| 条目包含的文件 | ||||||
| 条目无相关文件。 | ||||||
修改评论
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。