Boosting Time-series Domain Adaptation via A Time-Frequency Consensus Framework

doi:10.1109/TAI.2025.3571869

科研成果详情

题名	Boosting Time-series Domain Adaptation via A Time-Frequency Consensus Framework
作者	Yang，Wenmian 5; Ragab，Mohamed 1; Wu，Min 2; Pan，Sinno Jialin 3; Lin，Guosheng 4; Jia，Weijia 5,6; Chen，Zhenghua 2
发表日期	2025
发表期刊	IEEE Transactions on Artificial Intelligence
摘要	Unsupervised Domain Adaptation (UDA) has proven to be effective in addressing the domain shift problem in computer vision. However, compared with visual applications, UDA for time series brings forth additional challenges. Potential domain shifts may have varying impacts on both time and frequency features, rendering conventional UDA methods less effective in this context. To address these challenges, we propose a Time-Frequency Consensus Domain Adaption (TFCDA) framework to enhance UDA methods for time-series data. TFCDA designs a frequency encoder, a trainable Time-Frequency Mapping (TFM), and a consensus loss, building upon conventional UDA methods to boost their performance. The TFM is trained on source domain data to learn the inherent time-frequency feature mapping, while the novel consensus loss ensures consistent feature transfer during UDA in the target domain, effectively reducing domain shifts in both time and frequency, and thus boosting overall performance. Experimental evaluations on four publicly available time-series datasets demonstrate TFCDA's effectiveness in enhancing existing UDA methods for time-series data, highlighting its potential for real-world applications.
关键词	Domain Adaption Time-Frequency Consensus Time-series Transfer Learning
DOI	10.1109/TAI.2025.3571869
URL	查看来源
语种	英语English
Scopus入藏号	2-s2.0-105006897381
引用统计
文献类型	期刊论文
条目标识符	https://repository.uic.edu.cn/handle/39GCC9TT/13727
专题	北师香港浸会大学
通讯作者	Chen，Zhenghua
作者单位	1.Institute of Technology Innovation Institute,United Arab Emirates 2.Institute for Infocomm Research (I2R),A∗STAR,Singapore 3.The Chinese University of Hong Kong (CUHK),Department of Computer Science and Engineering,Hong Kong,Hong Kong 4.Nanyang Technological University,School of Computer Science and Engineering,Singapore 5.Beijing Normal University,Institute of Artificial Intelligence and Future Networks,Zhuhai,519087,China 6.BNUHKBU United International College,Guangdong Key Lab of AI and Multi-Modal Data Processing,Zhuhai,519087,China
推荐引用方式 GB/T 7714	Yang，Wenmian,Ragab，Mohamed,Wu，Minet al. Boosting Time-series Domain Adaptation via A Time-Frequency Consensus Framework[J]. IEEE Transactions on Artificial Intelligence, 2025.
APA	Yang，Wenmian., Ragab，Mohamed., Wu，Min., Pan，Sinno Jialin., Lin，Guosheng., .. & Chen，Zhenghua. (2025). Boosting Time-series Domain Adaptation via A Time-Frequency Consensus Framework. IEEE Transactions on Artificial Intelligence.
MLA	Yang，Wenmian,et al."Boosting Time-series Domain Adaptation via A Time-Frequency Consensus Framework". IEEE Transactions on Artificial Intelligence (2025).