SEA++: Multi-Graph-based Higher-Order Sensor Alignment for Multivariate Time-Series Unsupervised Domain Adaptation

Page view(s)
7
Checked on Nov 19, 2024
SEA++: Multi-Graph-based Higher-Order Sensor Alignment for Multivariate Time-Series Unsupervised Domain Adaptation
Title:
SEA++: Multi-Graph-based Higher-Order Sensor Alignment for Multivariate Time-Series Unsupervised Domain Adaptation
Journal Title:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Publication Date:
16 August 2024
Citation:
Wang, Y., Xu, Y., Yang, J., Wu, M., Li, X., Xie, L., & Chen, Z. (2024). SEA++: Multi-Graph-based Higher-Order Sensor Alignment for Multivariate Time-Series Unsupervised Domain Adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1–16. https://doi.org/10.1109/tpami.2024.3444904
Abstract:
Unsupervised Domain Adaptation (UDA) methods have been successful in reducing label dependency by minimizing the domain discrepancy between labeled source \textcolor{black}{domains} and unlabeled target \textcolor{black}{domains}. However, these methods face challenges when dealing with Multivariate Time-Series (MTS) data. MTS data typically \textcolor{black}{originates from} multiple sensors, each with \textcolor{black}{its unique distribution}. This \textcolor{black}{property poses difficulties in adapting existing UDA techniques}, which mainly focus on aligning global features while overlooking the distribution discrepancies at the sensor level, \textcolor{black}{thus limiting their effectiveness for MTS data}. To address this issue, a practical domain adaptation scenario is formulated as Multivariate Time-Series Unsupervised Domain Adaptation (MTS-UDA). In this paper, we propose SEnsor Alignment (SEA) for MTS-UDA, aiming to \textcolor{black}{address} domain discrepancy at both local and global sensor levels. At the local sensor level, we design endo-feature alignment, which aligns sensor features and their correlations across domains. To reduce domain discrepancy at the global sensor level, we design exo-feature alignment that enforces restrictions on global sensor features. We further extend SEA to SEA++ by enhancing the endo-feature alignment. Particularly, we incorporate multi-graph-based higher-order alignment for both sensor features and their correlations. Extensive empirical results have demonstrated the state-of-the-art performance of our SEA and SEA++ on \textcolor{black}{six} public MTS datasets for MTS-UDA.
License type:
Publisher Copyright
Funding Info:
This research / project is supported by the National Research Foundation, Singapore - AI Singapore Programme
Grant Reference no. : AISG2-RP-2021-027

This research / project is supported by the Agency for Science, Technology and Research - AME Programmatic Funds
Grant Reference no. : A20H6b0151
Description:
© 2024 IEEE.  Personal use of this material is permitted.  Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISSN:
0162-8828
2160-9292
1939-3539
Files uploaded:

File Size Format Action
tpami-sea.pdf 862.19 KB PDF Open