Research map / Time series / Foundation models for time series
SEnsor Alignment for Multivariate Time-Series Unsupervised Domain Adaptation
Yucheng Wang, Yuecong Xu, Jianfei Yang, Zhenghua Chen, Min Wu, Xiaoli Li, Lihua Xie
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use SEA instead of Coral | MTS-UDA · C-MAPSS cross-domain (12 scenarios) | RMSE: 25.22 -> 19.77 | Improved |
| Use SEA instead of CLUDA | MTS-UDA · C-MAPSS cross-domain (12 scenarios) | Score: 3511 -> 1963 | Improved |
| Use SEA instead of SDAT | MTS-UDA · Opportunity HAR cross-domain (12 scenarios) | accuracy: 81.07 -> 85.42 | Improved |
| Add endo-feature alignment, including sensor feature and correlation alignment (ablation) | SEA · C-MAPSS cross-domain (12 scenarios) | RMSE: 25.22 -> 19.77 | Improved |
| Add sensor correlation alignment (SCA) (ablation) | SEA · C-MAPSS cross-domain (12 scenarios) | RMSE: 21.97 -> 19.77 | Improved |
| Add sensor feature alignment (SFA) (ablation) | SEA · C-MAPSS cross-domain (12 scenarios) | RMSE: 22.77 -> 19.77 | Improved |
| Add endo-feature alignment, including sensor feature and correlation alignment (ablation) | SEA · C-MAPSS cross-domain (12 scenarios) | Score: 7237 -> 1963 | Improved |
| Add sensor correlation alignment (SCA) (ablation) | SEA · C-MAPSS cross-domain (12 scenarios) | Score: 3511 -> 1963 | Improved |
| Add sensor feature alignment (SFA) (ablation) | SEA · C-MAPSS cross-domain (12 scenarios) | Score: 3968 -> 1963 | Improved |
| Add endo-feature alignment, including sensor feature and correlation alignment (ablation) | SEA · Opportunity HAR cross-domain (12 scenarios) | accuracy: 80.47 -> 84.89 | Improved |
| Add sensor correlation alignment (SCA) (ablation) | SEA · Opportunity HAR cross-domain (12 scenarios) | accuracy: 82.00 -> 84.89 | Improved |
| Add sensor feature alignment (SFA) (ablation) | SEA · Opportunity HAR cross-domain (12 scenarios) | accuracy: 82.79 -> 84.89 | Improved |
Closest papers by meaning
- SEA++: Multi-Graph-Based Higher-Order Sensor Alignment for Multivariate Time-Series Unsupervised Domain Adaptation (TPAMI 2024 · similarity 0.97)
- Enhancing Multivariate Time-Series Domain Adaptation via Contrastive Frequency Graph Discovery and Language-Guided Adversary Alignment (AAAI 2025 · similarity 0.89)
- Breakthrough Sensor-Limited Single View: Towards Implicit Temporal Dynamics for Time Series Domain Adaptation (NeurIPS 2025 · similarity 0.89)
- Domain Adaptation for Time Series Under Feature and Label Shifts (ICML 2023 · similarity 0.87)
- Pseudo-Calibration: Improving Predictive Uncertainty Estimation in Unsupervised Domain Adaptation (ICML 2024 · similarity 0.87)
- CauDiTS: Causal Disentangled Domain Adaptation of Multivariate Time Series (ICML 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
