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