Research map / Time series / Foundation models for time series
SEA++: Multi-Graph-Based Higher-Order Sensor Alignment for Multivariate Time-Series Unsupervised Domain Adaptation
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 |
|---|---|---|---|
| add sensor correlation alignment (SCA) (ablation) | SEA++ (Exo only) · C-MAPSS | avg RMSE: 25.13 -> 22.42 (10.8%) | Improved |
| add sensor feature alignment (SFA) (ablation) | SEA++ (Exo only) · C-MAPSS | avg RMSE: 25.13 -> 21.96 (12.6%) | Improved |
| add multi-graph alignment (MGA) to SCA (ablation) | w/ Exo + SCA · C-MAPSS | avg RMSE: 22.42 -> 21.80 | Improved |
| add multi-graph alignment (MGA) to SFA (ablation) | w/ Exo + SFA · C-MAPSS | avg RMSE: 21.96 -> 21.40 | Improved |
| add second-order statistic alignment to SCA (ablation) | w/ Exo + SCA · C-MAPSS | avg RMSE: 22.42 -> 20.99 | Improved |
| add second-order statistic alignment to SFA (ablation) | w/ Exo + SFA · C-MAPSS | avg RMSE: 21.96 -> 21.06 | Improved |
| combine MGA and second-order (iSCA) (ablation) | w/ Exo + SCA · C-MAPSS | avg RMSE: 22.42 -> 20.54 | Improved |
| combine iSCA and iSFA (ablation) | w/ Exo only · C-MAPSS | avg RMSE: 25.13 -> 19.08 | Improved |
| add endo-feature alignment SCA (ablation) | w/ Exo only · Opportunity HAR | avg accuracy: 80.47 -> 82.79 | Improved |
| combine iSCA and iSFA (ablation) | w/ Exo only · Opportunity HAR | avg accuracy: 80.47 -> 88.18 | Improved |
| add SEA++ enhancements to SEA | SEA · C-MAPSS | avg RMSE: 19.56 -> 19.08 | Improved |
| add SEA++ enhancements to SEA | SEA · Opportunity HAR | avg accuracy: 85.42 -> 88.31 | Improved |
Closest papers by meaning
- SEnsor Alignment for Multivariate Time-Series Unsupervised Domain Adaptation (AAAI 2023 · 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 0.88)
- Towards Uncertainty-aware Unsupervised Domain Adaptation for Videos and Time-Series with Causal Optimal Transport (CVPR 2026 · similarity 0.87)
- Pseudo-Calibration: Improving Predictive Uncertainty Estimation in Unsupervised Domain Adaptation (ICML 2024 · similarity 0.86)
- Temporal Source Recovery for Time-Series Source-Free Unsupervised Domain Adaptation (TPAMI 2026 · similarity 0.86)
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.
