Research map / Time series / Foundation models for time series
Domain Adaptation for Time Series Under Feature and Label Shifts
Huan He, Owen Queen, Teddy Koker, Consuelo Cuevas, Theodoros Tsiligkaridis, Marinka Zitnik
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 Raincoat instead of the strongest baseline | UniDA · WISDM | H-score: 0.35 -> 0.52 | Improved |
| Use Raincoat instead of the strongest baseline | UniDA · WISDM→HHAR | H-score: 0.28 -> 0.52 | Improved |
| Use Raincoat instead of the strongest baseline | UniDA · HHAR→WISDM | H-score: 0.39 -> 0.47 | Improved |
| Add a time-frequency encoder (ablation) | Raincoat · HAR closed-set DA | accuracy: 82.48 -> 94.43 | Improved |
| Add a time-frequency encoder (ablation) | CLUDA · HAR closed-set DA | accuracy: 85.53 -> 90.62 | Improved |
| Add a frequency encoder to source-only training (ablation) | WISDM closed-set DA · WISDM | accuracy: 65.78 -> 75.22 | Improved |
| Add a frequency encoder to source-only training (ablation) | WISDM UniDA · WISDM | accuracy: 40.84 -> 42.97 | Improved |
| Add the correction step (ablation) | Raincoat with frequency encoder and MMD alignment · WISDM UniDA | accuracy: 42.97 -> 46.52 | Improved |
| Add the correction step (ablation) | Raincoat with frequency encoder and MMD alignment · WISDM closed-set DA | accuracy: 75.22 -> 76.04 | No clear effect |
| Use Sinkhorn instead of MMD for alignment (ablation) | Raincoat with frequency encoder · WISDM closed-set DA | accuracy: 1.02% | Improved |
| Use Sinkhorn instead of MMD for alignment (ablation) | Raincoat with frequency encoder · WISDM UniDA | accuracy: 1.11% | Improved |
| Add the time-frequency encoder (ablation) | Closed-set DA methods · HAR | accuracy | Improved |
Closest papers by meaning
- Boosting Transferability and Discriminability for Time Series Domain Adaptation (NeurIPS 2024 · similarity 0.88)
- Enhancing Multivariate Time-Series Domain Adaptation via Contrastive Frequency Graph Discovery and Language-Guided Adversary Alignment (AAAI 2025 · similarity 0.88)
- Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfer (ICML 2025 · similarity 0.86)
- A General Representation-Based Approach to Multi-Source Domain Adaptation (ICML 2025 · similarity 0.86)
- Large Pre-trained time series models for cross-domain Time series analysis tasks (NeurIPS 2024 · similarity 0.86)
- 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.
