Robust Multitask Learning With Sample Gradient Similarity
文献类型:期刊论文
作者 | Peng, Xinyu3; Chang, Cheng3; Wang, Fei-Yue2; Li, Li1 |
刊名 | IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS |
出版日期 | 2023-10-03 |
页码 | 10 |
ISSN号 | 2168-2216 |
关键词 | Deep learning Automation multitask learning sample gradient sample reweighting task reweighting |
DOI | 10.1109/TSMC.2023.3315541 |
通讯作者 | Li, Li(li-li@tsinghua.edu.cn) |
英文摘要 | Multitask learning has led to great success in many deep learning applications during the last decade. However, recent experiments have demonstrated that the performance of multitask learning depends on how to balance the relationship between different tasks. Therefore, many approaches have been proposed to adjust per-task gradient directions or design a more appropriate task reweighting scheme based on task-level statistics. In this article, we discuss how to boost the performance of multitask learning by using more fine-grained sample gradient information. To this end, we propose the concept of sample gradient similarity, which measures the agreement between the sample gradient for a task and the true gradient. Based on this concept, greater weight is assigned to more consistent tasks and more robust training samples to improve the training process of multitask learning. Extensive experimental results show that our proposed method outperforms the state-of-the-art algorithms on a series of challenging multitask datasets. |
WOS关键词 | INSTANCE SEGMENTATION ; OPTIMIZATION PROBLEMS ; NETWORK ; FUSION |
资助项目 | National Key Research and Development Program of China[2020AAA0108104] |
WOS研究方向 | Automation & Control Systems ; Computer Science |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:001086449200001 |
资助机构 | National Key Research and Development Program of China |
源URL | [http://ir.ia.ac.cn/handle/173211/54364] |
专题 | 多模态人工智能系统全国重点实验室 自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队 |
通讯作者 | Li, Li |
作者单位 | 1.Tsinghua Univ, Dept Automat, Tsinghua Natl Lab Informat Sci & Technol, Beijing 100084, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100080, Peoples R China 3.Tsinghua Univ, Dept Automat, Beijing 100084, Peoples R China |
推荐引用方式 GB/T 7714 | Peng, Xinyu,Chang, Cheng,Wang, Fei-Yue,et al. Robust Multitask Learning With Sample Gradient Similarity[J]. IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS,2023:10. |
APA | Peng, Xinyu,Chang, Cheng,Wang, Fei-Yue,&Li, Li.(2023).Robust Multitask Learning With Sample Gradient Similarity.IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS,10. |
MLA | Peng, Xinyu,et al."Robust Multitask Learning With Sample Gradient Similarity".IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS (2023):10. |
入库方式: OAI收割
来源:自动化研究所
浏览0
下载0
收藏0
其他版本
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。