Time Series Domain Adaptation via Channel-Selective Representation Alignment
Abstract: Building generalizable and robust multivariate time series models can be challenging for real-world settings that involve significant shifts between training and testing. Existing unsupervised domain adaptation methods often struggle with real world distribution shifts which are often much more severe in some channels than others. To overcome these obstacles, we introduce a novel method called Signal Selection and Screening via Sinkhorn alignment for Time Series domain Adaptation (SSSS-TSA). SSSS-TSA addresses channel-level variations by aligning both individual channel representations and selectively weighted combined channel representations. This dual alignment strategy based on channel selection not only ensures effective adaptation to new domains but also maintains robustness in scenarios with training and testing set shifts or when certain channels are absent or corrupted. We evaluate our method on several time-series classification benchmarks and find that it consistently improves performance over existing methods. These results demonstrate the importance of adaptively selecting and screening different channels to enable more effective alignment across domains.
Submission Length: Regular submission (no more than 12 pages of main content)
Assigned Action Editor: ~Mingsheng_Long2
Submission Number: 3555
Loading