# Population Aware Diffusion for Time Series Generation

arXiv: https://arxiv.org/abs/2501.00910 · HTML: https://mlsanity.com/paper/2501.00910/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in Flow matching, time series and science, one of 14 directions in Diffusion models.
- Builds on 24 of its 41 references that are in the map.
- First posted on arXiv 1 Jan 2025.

## Placed in

- Diffusion models / [Flow matching, time series and science](https://mlsanity.com/diffusion/flow-matching-time-series-and-science/)

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation](https://mlsanity.com/paper/2107.03502/) (2021)
- [Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm](https://mlsanity.com/paper/1608.04471/) (2016)
- [dm_control: Software and Tasks for Continuous Control](https://mlsanity.com/paper/2006.12983/) (2020)
- [Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2101.12072/) (2021)
- [Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs](https://mlsanity.com/paper/1706.02633/) (2017)
- [Diffusion-TS: Interpretable Diffusion for General Time Series Generation](https://mlsanity.com/paper/2403.01742/) (2024)
- [Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1705.00609/) (2017)
- [TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generation](https://mlsanity.com/paper/2111.08095/) (2021)
- [C-RNN-GAN: Continuous recurrent neural networks with adversarial training](https://mlsanity.com/paper/1611.09904/) (2016)
- [InfoVAE: Information Maximizing Variational Autoencoders](https://mlsanity.com/paper/1706.02262/) (2017)
- [Time Series Prediction using Deep Learning Methods in Healthcare](https://mlsanity.com/paper/2108.13461/) (2021)
- [On the Constrained Time-Series Generation Problem](https://mlsanity.com/paper/2307.01717/) (2023)
- [Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEs](https://mlsanity.com/paper/2310.02619/) (2023)
- [Towards Generating Real-World Time Series Data](https://mlsanity.com/paper/2111.08386/) (2021)
- [Financial Time Series Forecasting using CNN and Transformer](https://mlsanity.com/paper/2304.04912/) (2023)
- [TimeLDM: Latent Diffusion Model for Unconditional Time Series Generation](https://mlsanity.com/paper/2407.04211/) (2024)
- [SigDiffusions: Score-Based Diffusion Models for Time Series via Log-Signature Embeddings](https://mlsanity.com/paper/2406.10354/) (2024)

## Built on by (most cited first, 16 of 16)

- [Step-Aware Residual-Guided Diffusion for EEG Spatial Super-Resolution](https://mlsanity.com/paper/2510.19166/) (2025)
- [CTBench: Cryptocurrency Time Series Generation Benchmark](https://mlsanity.com/paper/2508.02758/) (2025)
- [WaveletDiff: Multilevel Wavelet Diffusion For Time Series Generation](https://mlsanity.com/paper/2510.11839/) (2025)
- [DiM-TS: Bridge the Gap between Selective State Space Models and Time Series for Generative Modeling](https://mlsanity.com/paper/2511.18312/) (2025)
- [SynEnergy: Anomaly Semantic-Guided Diffusion for Synthetic Energy Data Generation](https://mlsanity.com/paper/2608.03087/) (2026)
- [Critical Challenges and Guidelines in Evaluating Synthetic Tabular Data: A Systematic Review](https://mlsanity.com/paper/2504.18544/) (2025)
- [Selective Denoising Diffusion Model for Time Series Anomaly Detection](https://mlsanity.com/paper/2602.23662/) (2026)
- [Using Synthetic Data for Machine Learning-based Childhood Vaccination Prediction in Narok, Kenya](https://mlsanity.com/paper/2604.08902/) (2026)
- [TimeTok: Granularity-Controllable Time-Series Generation via Hierarchical Tokenization](https://mlsanity.com/paper/2605.01418/) (2026)
- [TriHead-GAN: A Generative Adversarial Network with Triple-Head Discriminator for Carbon Emission Time Series Generation](https://mlsanity.com/paper/2606.07569/) (2026)
- [Towards a Unified Generative Model for Scarce Time Series with Domain Experts](https://mlsanity.com/paper/2606.15172/) (2026)
- [MIDiff: Tackling Sparsity and Imbalance in Mobile Usage Generation via Multivariate-Imaging Diffusion](https://mlsanity.com/paper/2607.14249/) (2026)
- [Not All EEG Moments Are Equal: Position-Adaptive Time Scheduling for EEG Generation](https://mlsanity.com/paper/2608.00048/) (2026)
- [Physics-Guided Conditional Diffusion Model for Rare Event Synthesis and Diagnosis for the Water-Gas Shift Reaction](https://mlsanity.com/paper/2609.35499/) (2026)
- [ProCTI: Prototype-Refined Global Conditioning for Diffusion-Based Time Series Imputation](https://mlsanity.com/paper/2609.37632/) (2026)
- [Diffusion-Based Synthetic Data Pretraining for Enhancing Activity Recognition](https://mlsanity.com/paper/2610.02292/) (2026)

## Abstract (arXiv)

Diffusion models have shown promising ability in generating high-quality time series (TS) data. Despite the initial success, existing works mostly focus on the authenticity of data at the individual level, but pay less attention to preserving the population-level properties on the entire dataset. Such population-level properties include value distributions for each dimension and distributions of certain functional dependencies (e.g., cross-correlation, CC) between different dimensions. For instance, when generating house energy consumption TS data, the value distributions of the outside temperature and the kitchen temperature should be preserved, as well as the distribution of CC between them. Preserving such TS population-level properties is critical in maintaining the statistical insights of the datasets, mitigating model bias, and augmenting downstream tasks like TS prediction. Yet, it is often overlooked by existing models. Hence, data generated by existing models often bear distribution shifts from the original data. We propose Population-aware Diffusion for Time Series (PaD-TS), a new TS generation model that better preserves the population-level properties. The key novelties of PaD-TS include 1) a new training method explicitly incorporating TS population-level property preservation, and 2) a new dual-channel encoder model architecture that better captures the TS data structure. Empirical results in major benchmark datasets show that PaD-TS can improve the average CC distribution shift score between real and synthetic data by 5.9x while maintaining a performance comparable to state-of-the-art models on individual-level authenticity.