# MG-TSD: Multi-Granularity Time Series Diffusion Models with Guided Learning Process

arXiv: https://arxiv.org/abs/2403.05751 · HTML: https://mlsanity.com/paper/2403.05751/

## Key facts

- Cited by 32 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 20 of its 33 references that are in the map.
- First posted on arXiv 9 Mar 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, 20 of 20)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [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)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting](https://mlsanity.com/paper/2201.12740/) (2022)
- [Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks](https://mlsanity.com/paper/1703.07015/) (2017)
- [Masked Autoregressive Flow for Density Estimation](https://mlsanity.com/paper/1705.07057/) (2017)
- [CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation](https://mlsanity.com/paper/2107.03502/) (2021)
- [Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2101.12072/) (2021)
- [High-Dimensional Multivariate Forecasting with Low-Rank Gaussian Copula Processes](https://mlsanity.com/paper/1910.03002/) (2019)
- [Multivariate Probabilistic Time Series Forecasting via Conditioned Normalizing Flows](https://mlsanity.com/paper/2002.06103/) (2020)
- [Generative Time Series Forecasting with Diffusion, Denoise, and Disentanglement](https://mlsanity.com/paper/2301.03028/) (2023)
- [Generating High Fidelity Data from Low-density Regions using Diffusion Models](https://mlsanity.com/paper/2203.17260/) (2022)
- [Non-autoregressive Conditional Diffusion Models for Time Series Prediction](https://mlsanity.com/paper/2306.05043/) (2023)
- [TACTiS: Transformer-Attentional Copulas for Time Series](https://mlsanity.com/paper/2202.03528/) (2022)

## Built on by (most cited first, 30 of 32)

- [Retrieval-Augmented Diffusion Models for Time Series Forecasting](https://mlsanity.com/paper/2410.18712/) (2024)
- [TimeDP: Learning to Generate Multi-Domain Time Series with Domain Prompts](https://mlsanity.com/paper/2501.05403/) (2025)
- [BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modeling](https://mlsanity.com/paper/2503.02445/) (2025)
- [CrossAD: Time Series Anomaly Detection with Cross-scale Associations and Cross-window Modeling](https://mlsanity.com/paper/2510.12489/) (2025)
- [ANT: Adaptive Noise Schedule for Time Series Diffusion Models](https://mlsanity.com/paper/2410.14488/) (2024)
- [Diffusion Models for Time Series Forecasting: A Survey](https://mlsanity.com/paper/2507.14507/) (2025)
- [Auto-Regressive Moving Diffusion Models for Time Series Forecasting](https://mlsanity.com/paper/2412.09328/) (2024)
- [Multimodal Conditioned Diffusive Time Series Forecasting](https://mlsanity.com/paper/2504.19669/) (2025)
- [TarDiff: Target-Oriented Diffusion Guidance for Synthetic Electronic Health Record Time Series Generation](https://mlsanity.com/paper/2504.17613/) (2025)
- [TimeAutoDiff: A Unified Framework for Generation, Imputation, Forecasting, and Time-Varying Metadata Conditioning of Heterogeneous Time Series Tabular Data](https://mlsanity.com/paper/2406.16028/) (2024)
- [InvDiff: Invariant Guidance for Bias Mitigation in Diffusion Models](https://mlsanity.com/paper/2412.08480/) (2024)
- [Series-to-Series Diffusion Bridge Model](https://mlsanity.com/paper/2411.04491/) (2024)
- [Adaptive Two-Stage Cloud Resource Scaling via Hierarchical Multi-Indicator Forecasting and Bayesian Decision-Making](https://mlsanity.com/paper/2408.01000/) (2024)
- [Channel-aware Contrastive Conditional Diffusion for Multivariate Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2410.02168/) (2024)
- [DS-Diffusion: Data Style-Guided Diffusion Model for Time-Series Generation](https://mlsanity.com/paper/2509.18584/) (2025)
- [MS-SSM: A Multi-Scale State Space Model for Efficient Sequence Modeling](https://mlsanity.com/paper/2512.23824/) (2025)
- [Stochastic Diffusion: A Diffusion Probabilistic Model for Stochastic Time Series Forecasting](https://mlsanity.com/paper/2406.02827/) (2024)
- [Diffolio: A Diffusion Model for Multivariate Probabilistic Financial Time-Series Forecasting and Portfolio Construction](https://mlsanity.com/paper/2511.07014/) (2025)
- [CHIME: Conditional Hallucination and Integrated Multi-scale Enhancement for Time Series Diffusion Model](https://mlsanity.com/paper/2506.03502/) (2025)
- [MGTraj: Multi-Granularity Goal-Guided Human Trajectory Prediction with Recursive Refinement Network](https://mlsanity.com/paper/2509.09200/) (2025)
- [Denoising Refinement Diffusion Models for Simultaneous Generation of Multi-scale Mobile Network Traffic](https://mlsanity.com/paper/2511.17532/) (2025)
- [SimDiff: Simpler Yet Better Diffusion Model for Time Series Point Forecasting](https://mlsanity.com/paper/2511.19256/) (2025)
- [Short-term electricity load forecasting with multi-frequency reconstruction diffusion](https://mlsanity.com/paper/2601.06533/) (2026)
- [A Decomposable Forward Process in Diffusion Models for Time-Series Forecasting](https://mlsanity.com/paper/2601.21812/) (2026)
- [Enhancing few-shot time series forecasting with LLM-guided diffusion](https://mlsanity.com/paper/2602.00040/) (2026)
- [Deep Generative Transformers for Probabilistic Time Series and Spatiotemporal Forecasting](https://mlsanity.com/paper/2603.11909/) (2026)
- [Deep Time-Series Forecasting in 10 Years: A Survey](https://mlsanity.com/paper/2603.19899/) (2026)
- [TimeTok: Granularity-Controllable Time-Series Generation via Hierarchical Tokenization](https://mlsanity.com/paper/2605.01418/) (2026)
- [IGADA-IoT: IoT Sensor Energy Optimization in Wireless Sensor Networks Driven by Automatic Data Augmentation](https://mlsanity.com/paper/2605.27397/) (2026)
- [Differencing the Diffusion Trajectory toward Uncertain Components for Time Series Forecasting](https://mlsanity.com/paper/2607.22599/) (2026)

## Abstract (arXiv)

Recently, diffusion probabilistic models have attracted attention in generative time series forecasting due to their remarkable capacity to generate high-fidelity samples. However, the effective utilization of their strong modeling ability in the probabilistic time series forecasting task remains an open question, partially due to the challenge of instability arising from their stochastic nature. To address this challenge, we introduce a novel Multi-Granularity Time Series Diffusion (MG-TSD) model, which achieves state-of-the-art predictive performance by leveraging the inherent granularity levels within the data as given targets at intermediate diffusion steps to guide the learning process of diffusion models. The way to construct the targets is motivated by the observation that the forward process of the diffusion model, which sequentially corrupts the data distribution to a standard normal distribution, intuitively aligns with the process of smoothing fine-grained data into a coarse-grained representation, both of which result in a gradual loss of fine distribution features. In the study, we derive a novel multi-granularity guidance diffusion loss function and propose a concise implementation method to effectively utilize coarse-grained data across various granularity levels. More importantly, our approach does not rely on additional external data, making it versatile and applicable across various domains. Extensive experiments conducted on real-world datasets demonstrate that our MG-TSD model outperforms existing time series prediction methods.