Research map / Time series / Causal and generative time series
Time-series Generative Adversarial Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 stepwise supervised loss (ablation) | TimeGAN · Sines | discriminative score: .193 -> .011 | Helped |
| add stepwise supervised loss (ablation) | TimeGAN · Stocks | predictive score: .054 -> .038 | Helped |
| add embedding network (ablation) | TimeGAN · Stocks | discriminative score: .260 -> .102 | Helped |
| add embedding network (ablation) | TimeGAN · Events | predictive score: .410 -> .303 | Helped |
| jointly train embedding with supervised loss (ablation) | TimeGAN · Sines | discriminative score: .048 -> .011 | Helped |
| TimeGAN vs RCGAN | time-series generation · Stocks | discriminative score: .196 -> .102 | Helped |
| TimeGAN vs RCGAN | time-series generation · Events | discriminative score: .380 -> .161 | Helped |
| TimeGAN vs C-RNN-GAN | time-series generation · Stocks | predictive score: .038 vs .038 | No clear effect |
| higher temporal correlation phi (0.2 -> 0.8) | TimeGAN advantage over RCGAN · AR Gaussian | discriminative score: .177 vs .175 -> .133 vs .105 | Helped |
Closest papers by meaning
- AEC-GAN: Adversarial Error Correction GANs for Auto-Regressive Long Time-Series Generation (AAAI 2023 · similarity 0.91)
- Time Series Generation Under Data Scarcity: A Unified Generative Modeling Approach (NeurIPS 2025 · similarity 0.90)
- Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEs (ICLR 2024 · similarity 0.87)
- TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting (ICLR 2024 · similarity 0.87)
- Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series (NeurIPS 2024 · similarity 0.87)
- TimeTok: Granularity-Controllable Time-Series Generation via Hierarchical Tokenization (NeurIPS 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.