# Deep Temporal Deaggregation: Large-Scale Spatio-Temporal Generative Models

arXiv: https://arxiv.org/abs/2406.12423 · HTML: https://mlsanity.com/paper/2406.12423/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 42 references that are in the map.
- First posted on arXiv 18 Jun 2024.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://mlsanity.com/paper/2009.09761/) (2020)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation](https://mlsanity.com/paper/2107.03502/) (2021)
- [Tackling the Generative Learning Trilemma with Denoising Diffusion GANs](https://mlsanity.com/paper/2112.07804/) (2021)
- [Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs](https://mlsanity.com/paper/1706.02633/) (2017)
- [Unsupervised Scalable Representation Learning for Multivariate Time Series](https://mlsanity.com/paper/1901.10738/) (2019)
- [Diffusion-based Time Series Imputation and Forecasting with Structured State Space Models](https://mlsanity.com/paper/2208.09399/) (2022)
- [How Faithful is your Synthetic Data? Sample-level Metrics for Evaluating and Auditing Generative Models](https://mlsanity.com/paper/2102.08921/) (2021)
- [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)
- [Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2307.11494/) (2023)
- [Non-autoregressive Conditional Diffusion Models for Time Series Prediction](https://mlsanity.com/paper/2306.05043/) (2023)
- [PSA-GAN: Progressive Self Attention GANs for Synthetic Time Series](https://mlsanity.com/paper/2108.00981/) (2021)
- [GT-GAN: General Purpose Time Series Synthesis with Generative Adversarial Networks](https://mlsanity.com/paper/2210.02040/) (2022)
- [Continuous Trajectory Generation Based on Two-Stage GAN](https://mlsanity.com/paper/2301.07103/) (2023)
- [COLA: Cross-city Mobility Transformer for Human Trajectory Simulation](https://mlsanity.com/paper/2403.01801/) (2024)
- [Generating multivariate time series with COmmon Source CoordInated GAN (COSCI-GAN)](https://mlsanity.com/paper/2205.13741/) (2022)
- [Bridging Explicit and Implicit Deep Generative Models via Neural Stein Estimators](https://mlsanity.com/paper/1909.13035/) (2019)

## Abstract (arXiv)

Many of today's data is time-series data originating from various sources, such as sensors, transaction systems, or production systems. Major challenges with such data include privacy and business sensitivity. Generative time-series models have the potential to overcome these problems, allowing representative synthetic data, such as people's movement in cities, to be shared openly and be used to the benefit of society at large. However, contemporary approaches are limited to prohibitively short sequences and small scales. Aside from major memory limitations, the models generate less accurate and less representative samples the longer the sequences are. This issue is further exacerbated by the lack of a comprehensive and accessible benchmark. Furthermore, a common need in practical applications is what-if analysis and dynamic adaptation to data distribution changes, for usage in decision making and to manage a changing world: What if this road is temporarily blocked or another road is added? The focus of this paper is on mobility data, such as people's movement in cities, requiring all these issues to be addressed. To this end, we propose a transformer-based diffusion model, TDDPM, for time-series which outperforms and scales substantially better than state-of-the-art. This is evaluated in a new comprehensive benchmark across several sequence lengths, standard datasets, and evaluation measures. We also demonstrate how the model can be conditioned on a prior over spatial occupancy frequency information, allowing the model to generate mobility data for previously unseen environments and for hypothetical scenarios where the underlying road network and its usage changes. This is evaluated by training on mobility data from part of a city. Then, using only aggregate spatial information as prior, we demonstrate out-of-distribution generalization to the unobserved remainder of the city.