# L-GTA: Latent Generative Modeling for Time Series Augmentation

arXiv: https://arxiv.org/abs/2507.23615 · HTML: https://mlsanity.com/paper/2507.23615/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 33 references that are in the map.
- First posted on arXiv 31 Jul 2025.

## Builds on (most cited first, 8 of 8)

- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [A Recurrent Latent Variable Model for Sequential Data](https://mlsanity.com/paper/1506.02216/) (2015)
- [Time Series Data Augmentation for Deep Learning: A Survey](https://mlsanity.com/paper/2002.12478/) (2020)
- [Diffusion-TS: Interpretable Diffusion for General Time Series Generation](https://mlsanity.com/paper/2403.01742/) (2024)
- [TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generation](https://mlsanity.com/paper/2111.08095/) (2021)
- [An Empirical Survey of Data Augmentation for Time Series Classification with Neural Networks](https://mlsanity.com/paper/2007.15951/) (2020)
- [Sig-Wasserstein GANs for Time Series Generation](https://mlsanity.com/paper/2111.01207/) (2021)
- [GRATIS: GeneRAting TIme Series with diverse and controllable characteristics](https://mlsanity.com/paper/1903.02787/) (2019)

## Built on by (most cited first, 1 of 1)

- [ASTER: Latent Pseudo-Anomaly Generation for Unsupervised Time-Series Anomaly Detection](https://mlsanity.com/paper/2604.13924/) (2026)

## Abstract (arXiv)

Data augmentation is becoming increasingly important across various areas of time series analysis, including forecasting, classification, and anomaly detection. We introduce the Latent Generative Temporal Augmentation (L-GTA) model, a generative approach based on a Variational Autoencoder with a Bi-LSTM backbone and temporal self-attention. The model learns a latent representation for each timestep and applies controlled perturbations such as jittering, magnitude warping, or drift. We define an equivariance objective to further encourage consistency between latent space and data space transformations. As a result, the augmented samples show predictable and interpretable transformation signatures. We evaluate L-GTA on several real-world datasets against SOTA generative methods, including TimeGAN, TimeVAE, and Diffusion-TS, as well as direct transformation approaches. Across experiments on downstream forecasting, distribution fidelity, and controllability of transformation intensity, L-GTA consistently outperforms competing approaches. In downstream forecasting, it reduces prediction error by up to 26% compared to the strongest generative method and 27% relative to using the original data without augmentation.