Robust Multitask Learning With Sample Gradient Similarity

doi:10.1109/TSMC.2023.3315541

CORC > 自动化研究所 > 中国科学院自动化研究所 > 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

	Robust Multitask Learning With Sample Gradient Similarity
	Peng, Xinyu 3; Chang, Cheng 3; Wang, Fei-Yue 2; Li, Li 1
刊名	IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
	2023-10-03
页码	10
关键词	Deep learning Automation multitask learning sample gradient sample reweighting task reweighting
ISSN号	2168-2216
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.
资助项目	National Key Research and Development Program of China[2020AAA0108104]
WOS关键词	INSTANCE SEGMENTATION ; OPTIMIZATION PROBLEMS ; NETWORK ; FUSION
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
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/54364]
专题	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.