Grouped Multi-Task Learning with Hidden Tasks Enhancement

doi:10.3233/FAIA230392

	Grouped Multi-Task Learning with Hidden Tasks Enhancement
	Jin, Jiachun1 ; Wang, Jiankun1 ; Sun, Lu1 ; Zheng, Jie1 ; Kudo, Mineichi 2
	2023-09-28
会议录名称	FRONTIERS IN ARTIFICIAL INTELLIGENCE AND APPLICATIONS
ISSN	0922-6389
卷号	372
页码	1164-1171
DOI	10.3233/FAIA230392
摘要	In multi-task learning (MTL), multiple prediction tasks are learned jointly, such that generalization performance is improved by transferring information across the tasks. However, not all tasks are related, and training unrelated tasks together can worsen the prediction performance because of the phenomenon of negative transfer. To overcome this problem, we propose a novel MTL method that can robustly group correlated tasks into clusters and allow useful information to be transferred only within clusters. The proposed method is based on the assumption that the task clusters lie in the low-rank subspaces of the parameter space, and the number of them and their dimensions are both unknown. By applying subspace clustering to task parameters, parameter learning and task grouping can be done in a unified framework. To relieve the error induced by the basic linear learner and robustify the model, the effect of hidden tasks is exploited. Moreover, the framework is extended to a multi-layer architecture so as to progressively extract hierarchical subspace structures of tasks, which helps to further improve generalization. The optimization algorithm is proposed, and its effectiveness is validated by experimental results on both synthetic and real-world datasets. © 2023 The Authors.
会议录编者/会议主办者	Amazon Alexa ; APTIV ; et al. ; Hewlett Packard ; IDEAS ; Software Force
关键词	Clustering algorithms Learning systems Machine learning Generalization performance Learning methods Multitask learning Parameter learning Parameter spaces Prediction performance Prediction tasks Subspace clustering Unified framework Within clusters
会议名称	26th European Conference on Artificial Intelligence, ECAI 2023
会议地点	Krakow, Poland
会议日期	September 30, 2023 - October 4, 2023
URL	查看原文
收录类别	EI
语种	英语
出版者	IOS Press BV
EI入藏号	20234515035050
EI主题词	Linearization
EISSN	1879-8314
EI分类号	723.4 Artificial Intelligence ; 903.1 Information Sources and Analysis
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/346435
专题	信息科学与技术学院_硕士生信息科学与技术学院_PI研究组_郑杰组信息科学与技术学院_PI研究组_孙露组
作者单位	1.ShanghaiTech University, China; 2.Hokkaido University, Japan
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	Jin, Jiachun,Wang, Jiankun,Sun, Lu,et al. Grouped Multi-Task Learning with Hidden Tasks Enhancement[C]//Amazon Alexa, APTIV, et al., Hewlett Packard, IDEAS, Software Force:IOS Press BV,2023:1164-1171.