Research map / Time series / Foundation models for time series
Training Robust Deep Models for Time-Series Domain: Novel Algorithms and Theoretical Analysis
Taha Belkhouja, Yan Yan, Janardhan Rao Doppa
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 RO-TS instead of FGS adversarial training | 1D-CNN time-series classifiers · MoteStrain | accuracy under adversarial and Gaussian noise | Improved |
| Use RO-TS instead of PGD adversarial training | 1D-CNN time-series classifiers · UCR time-series datasets | accuracy under adversarial noise | Improved |
| Use RO-TS instead of FGS adversarial training | 1D-CNN time-series classifiers · UCR time-series datasets | accuracy under Gaussian noise | Improved |
| Use RO-TS instead of stability training | 1D-CNN time-series classifiers · UCR time-series datasets | accuracy under adversarial and Gaussian perturbations | Improved |
| Use GAK distance instead of L2 distance (ablation) | RO-TS · ECG5000 | accuracy under perturbations | Improved |
| Use GAK distance instead of L2 distance (ablation) | RO-TS · ERing | accuracy under perturbations | Improved |
| Use GAK distance instead of L2 distance (ablation) | RO-TS · RacketSports | accuracy under perturbations | Improved |
| Use GAK distance instead of L2 distance (ablation) | RO-TS · SyntheticControl | accuracy under perturbations | No clear effect |
| Use GAK distance instead of L2 distance (ablation) | RO-TS · ArticularyWR | accuracy under perturbations | No clear effect |
| Estimate GAK using sampled alignments rather than all alignment paths (ablation) | RO-TS · ERing | accuracy gap | Improved |
| Use sampled alignments rather than all alignment paths (ablation) | RO-TS · ERing | computational runtime | Improved |
Closest papers by meaning
- SynTSBench: Rethinking Temporal Pattern Learning in Deep Learning Models for Time Series (NeurIPS 2025 · similarity 0.88)
- Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts (ICLR 2025 · similarity 0.87)
- Timer: Generative Pre-trained Transformers Are Large Time Series Models (ICML 2024 · similarity 0.85)
- TStruct: Learning Shared Temporal Structures for Long-Term Time-Series Forecasting (NeurIPS 2026 · similarity 0.85)
- Hierarchical Classification Auxiliary Network for Time Series Forecasting (AAAI 2025 · similarity 0.85)
- Fortifying Time Series: DTW-Certified Robust Anomaly Detection (NeurIPS 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.
