REGEN: Reference-Guided Synthetic Multivariate Time Series Generation for Forecasting
About
Training robust multivariate time series forecasting models requires large, diverse corpora, yet many real-world domains provide only a handful of observed sequences. Existing generators fail to resolve this mismatch: prior-based approaches (e.g., CauKer, TimePFN) produce domain-agnostic samples, while data-driven methods (e.g., TimeGAN) treat references as black-box supervision, forfeiting explicit control over periodic structure, local variability, and cross-variable dynamics. We propose ReGeN, a reference-guided generative pipeline that treats observed sequences not as examples to imitate, but as structural scaffolds for controllable synthesis. ReGeN decomposes each reference into three interpretable components: a phase-aligned periodic backbone capturing dominant domain morphology; per-variable stochastic residuals modeled with a deep-kernel Gaussian process; and lag-aware cross-variable dependencies injected through a structural causal model with fitted coupling coefficients. Sampling these components at controllable temperature broadens distributional coverage while preserving domain-grounded structure. We show that ReGeN-generated data consistently substitutes for real sibling data with minimal forecasting degradation, and in strongly periodic domains such as traffic, can outperform the real source itself. We further show that a foundation model pretrained on ReGeN corpora outperforms those pretrained on prior-based and data-driven synthetic alternatives. This suggests that in low-data regimes, how reference data is structurally exploited can matter as much as how much data is available.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Time Series Forecasting | PeMS08 | MSE0.3 | 232 | |
| Time Series Forecasting | PeMS04 | MSE0.37 | 172 | |
| Forecasting | Hog | MAE0.48 | 23 | |
| Forecasting | bull | MAE0.4 | 23 | |
| Time Series Forecasting | Full-corpus Time-series | MSE231.1 | 3 | |
| Time Series Forecasting | Subseasonal | MSE0.4 | 3 | |
| Time Series Forecasting | Sub. precip. | MSE1.01 | 3 | |
| Time Series Forecasting | Residential Load | MSE0.54 | 3 | |
| Time Series Forecasting | BEAR | MSE0.41 | 3 | |
| Time Series Forecasting | PANTHER | MSE0.36 | 3 |