Research map / Time series / Foundation models for time series
Contrastive Learning for Unsupervised Domain Adaptation of Time Series
Yilmazcan Ozyurt, Stefan Feuerriegel, Ce Zhang
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 contrastive learning (MoCo) and nearest-neighbor CL alignment on top of adversarial training (full CLUDA vs. w/o CL and w/o NNCL) (ablation) | domain adversarial base architecture · WISDM, HAR, HHAR benchmarks | accuracy | Improved |
| Remove the discriminator from CLUDA (w/o Discriminator) (ablation) | CLUDA · benchmark datasets | accuracy: discriminator gives consistent but smaller gains | Improved |
| Replace MoCo-based CL with SimCLR or NCL in CLUDA (ablation) | CLUDA · benchmark datasets | accuracy | Hurt |
| CLUDA vs. best baseline AdvSKM on MIMIC mortality | MIMIC-IV mortality UDA · MIMIC-IV 12 scenarios | AUROC: +2.2% relative (0.773 vs 0.756) | Improved |
| Use CLUDA instead of no-UDA on AUMC decompensation | AUMC decompensation UDA · MIMIC to AUMC | AUROC: fills 47.6% of performance gap vs 16.7% for best baseline HoMM | Improved |
| Most UDA baselines (CAN, CDAN, DDC, DeepCORAL, DSAN, HoMM, MMDA, CoDATS) applied to MIMIC mortality | MIMIC-IV mortality UDA · MIMIC-IV 12 scenarios | AUROC (avg): CDAN 0.721 below w/o UDA 0.750; VRADA 0.745 and AdvSKM 0.756 vary by scenario | Mixed |
Closest papers by meaning
- Enhancing Multivariate Time-Series Domain Adaptation via Contrastive Frequency Graph Discovery and Language-Guided Adversary Alignment (AAAI 2025 · similarity 0.90)
- SimProF: A Simple Probabilistic Framework for Unsupervised Domain Adaptation (AAAI 2025 · similarity 0.86)
- Cross-Domain Contrastive Learning for Time Series Clustering (AAAI 2024 · similarity 0.86)
- CauDiTS: Causal Disentangled Domain Adaptation of Multivariate Time Series (ICML 2024 · similarity 0.85)
- Boosting Transferability and Discriminability for Time Series Domain Adaptation (NeurIPS 2024 · similarity 0.85)
- Link-based Contrastive Learning for One-Shot Unsupervised Domain Adaptation (CVPR 2025 · 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.
