# TimeAutoDiff: A Unified Framework for Generation, Imputation, Forecasting, and Time-Varying Metadata Conditioning of Heterogeneous Time Series Tabular Data

arXiv: https://arxiv.org/abs/2406.16028 · HTML: https://mlsanity.com/paper/2406.16028/

## Key facts

- Cited by 5 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 54 of its 75 references that are in the map.
- First posted on arXiv 23 Jun 2024.

## 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, 30 of 54)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting](https://mlsanity.com/paper/2012.07436/) (2020)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Are Transformers Effective for Time Series Forecasting?](https://mlsanity.com/paper/2205.13504/) (2022)
- [On the Spectral Bias of Neural Networks](https://mlsanity.com/paper/1806.08734/) (2018)
- [TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis](https://mlsanity.com/paper/2210.02186/) (2022)
- [iTransformer: Inverted Transformers Are Effective for Time Series Forecasting](https://mlsanity.com/paper/2310.06625/) (2023)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [Time-LLM: Time Series Forecasting by Reprogramming Large Language Models](https://mlsanity.com/paper/2310.01728/) (2023)
- [Modeling Tabular data using Conditional GAN](https://mlsanity.com/paper/1907.00503/) (2019)
- [A decoder-only foundation model for time-series forecasting](https://mlsanity.com/paper/2310.10688/) (2023)
- [Equivariant Diffusion for Molecule Generation in 3D](https://mlsanity.com/paper/2203.17003/) (2022)
- [Score-based Generative Modeling in Latent Space](https://mlsanity.com/paper/2106.05931/) (2021)
- [CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation](https://mlsanity.com/paper/2107.03502/) (2021)
- [MOMENT: A Family of Open Time-series Foundation Models](https://mlsanity.com/paper/2402.03885/) (2024)
- [TabTransformer: Tabular Data Modeling Using Contextual Embeddings](https://mlsanity.com/paper/2012.06678/) (2020)
- [TabDDPM: Modelling Tabular Data with Diffusion Models](https://mlsanity.com/paper/2209.15421/) (2022)
- [TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting](https://mlsanity.com/paper/2405.14616/) (2024)
- [Geometric Latent Diffusion Models for 3D Molecule Generation](https://mlsanity.com/paper/2305.01140/) (2023)
- [Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space](https://mlsanity.com/paper/2310.09656/) (2023)
- [Data Synthesis based on Generative Adversarial Networks](https://mlsanity.com/paper/1806.03384/) (2018)
- [Diffusion-TS: Interpretable Diffusion for General Time Series Generation](https://mlsanity.com/paper/2403.01742/) (2024)
- [CTAB-GAN: Effective Table Data Synthesizing](https://mlsanity.com/paper/2102.08369/) (2021)
- [FiLM: Frequency improved Legendre Memory Model for Long-term Time Series Forecasting](https://mlsanity.com/paper/2205.08897/) (2022)

## Built on by (most cited first, 5 of 5)

- [WaveletDiff: Multilevel Wavelet Diffusion For Time Series Generation](https://mlsanity.com/paper/2510.11839/) (2025)
- [Learning What Not to Impute: An Uncertainty-Aware Diffusion Framework for Meaningful Missingness](https://mlsanity.com/paper/2606.05073/) (2026)
- [Diffusion-Driven State Space Models](https://mlsanity.com/paper/2606.21036/) (2026)
- [MIDiff: Tackling Sparsity and Imbalance in Mobile Usage Generation via Multivariate-Imaging Diffusion](https://mlsanity.com/paper/2607.14249/) (2026)
- [Synthesis Without Training: An Inference-Only Pipeline for Tabular, Temporal, and Relational Synthetic Data](https://mlsanity.com/paper/2609.38414/) (2026)

## Abstract (arXiv)

We present TimeAutoDiff, a unified latent-diffusion framework for four fundamental time-series tasks: unconditional generation, missing-data imputation, forecasting, and time-varying-metadata conditional generation. The model natively supports heterogeneous features including continuous, binary, and categorical variables. We unify all tasks using a masked-modeling strategy in which a binary mask specifies which time-series cells are observed and which must be generated. TimeAutoDiff combines a lightweight variational autoencoder, which maps mixed-type features into a continuous latent sequence, with a diffusion model that learns temporal dynamics in this latent space. Two architectural choices provide strong speed and scalability benefits. The diffusion model samples an entire latent trajectory at once rather than denoising one timestep at a time, greatly reducing reverse-diffusion calls. In addition, the VAE compresses along the feature axis, enabling efficient modeling of wide tables in a low-dimensional latent space. Empirical evaluation shows that TimeAutoDiff matches or surpasses strong baselines in synthetic sequence fidelity and consistently improves imputation and forecasting performance. Metadata conditioning enables realistic scenario exploration, allowing users to edit metadata sequences and produce coherent counterfactual trajectories that preserve cross-feature dependencies. Ablation studies highlight the importance of the VAE's feature encoding and key components of the denoiser. A distance-to-closest-record audit further indicates that the model generalizes without excessive memorization. Code is available at https://github.com/namjoonsuh/TimeAutoDiff