mlsanityData to 7 Oct 2026

Diff-MN: Diffusion Parameterized MoE-NCDE for Continuous Time Series Generation with Irregular Observations

arXiv 2601.13534 ↗First posted 20 Jan 2026cs.LG cs.AIcited by 2

On the map: Mixture-of-experts → MoE for time series and graphs

Abstract (arXiv)

Time series generation (TSG) is widely used across domains, yet most existing methods assume regular sampling and fixed output resolutions. These assumptions are often violated in practice, where observations are irregular and sparse, while downstream applications require continuous and high-resolution TS. Although Neural Controlled Differential Equation (NCDE) is promising for modeling irregular TS, it is constrained by a single dynamics function, tightly coupled optimization, and limited ability to adapt learned dynamics to newly generated samples from the generative model. We propose Diff-MN, a continuous TSG framework that enhances NCDE with a Mixture-of-Experts (MoE) dynamics function and a decoupled architectural design for dynamics-focused training. To further enable NCDE to generalize to newly generated samples, Diff-MN employs a diffusion model to parameterize the NCDE temporal dynamics parameters (MoE weights), i.e., jointly learn the distribution of TS data and MoE weights. This design allows sample-specific NCDE parameters to be generated for continuous TS generation. Experiments on ten public and synthetic datasets demonstrate that Diff-MN consistently outperforms strong baselines on both irregular-to-regular and irregular-to-continuous TSG tasks. The code is available at the link https://github.com/microsoft/TimeCraft/tree/main/Diff-MN.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in MoE for time series and graphs, one of 12 directions in Mixture-of-experts. Builds on 24 of its 43 references that are in the map. First posted on arXiv 20 Jan 2026.

Builds on

24 of 43 references.

References · 24

  1. 2018Neural Ordinary Differential Equationscited by 3,733
  2. 2016Recurrent Neural Networks for Multivariate Time Series with Missing Valuescited by 548
  3. 2020Neural Controlled Differential Equations for Irregular Time Seriescited by 501
  4. 2021TimeVAE: A Variational Auto-Encoder for Multivariate Time Series Generationcited by 139
  5. 2023Diffusion Models for Time Series Applications: A Surveycited by 72
  6. 2023Vector Quantized Time Series Generation with a Bidirectional Prior Modelcited by 49
  7. 2023Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEscited by 48
  8. 2022GT-GAN: General Purpose Time Series Synthesis with Generative Adversarial Networkscited by 43
  9. 2020Modeling Continuous Stochastic Processes with Dynamic Normalizing Flowscited by 37
  10. 2018T-CGAN: Conditional Generative Adversarial Network for Data Augmentation in Noisy Time Series with Irregular Samplingcited by 29
  11. 2023Reliable Generation of Privacy-preserving Synthetic Electronic Health Record Time Series via Diffusion Modelscited by 24
  12. 2025TimeDP: Learning to Generate Multi-Domain Time Series with Domain Promptscited by 21
12 more
  1. 2025MIRA: Medical Time Series Foundation Model for Real-World Health Datacited by 21
  2. 2023Irregular Traffic Time Series Forecasting Based on Asynchronous Spatio-Temporal Graph Convolutional Networkcited by 19
  3. 2025T2S: High-resolution Time Series Generation with Text-to-Series Diffusion Modelscited by 19
  4. 2025BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modelingcited by 18
  5. 2023TSGM: A Flexible Framework for Generative Modeling of Synthetic Time Seriescited by 16
  6. 2025Multi-period Learning for Financial Time Series Forecastingcited by 11
  7. 2025TarDiff: Target-Oriented Diffusion Guidance for Synthetic Electronic Health Record Time Series Generationcited by 8
  8. 2025Causal Time Series Generation via Diffusion Modelscited by 7
  9. 2023TS-Diffusion: Generating Highly Complex Time Series with Diffusion Modelscited by 6
  10. 2025CENTS: Generating synthetic electricity consumption time series for rare and unseen scenarioscited by 3
  11. 2025TSGM: Regular and Irregular Time-series Generation using Score-based Generative Modelscited by 3
  12. 2023Volatility and irregularity Capturing in stock price indices using time series Generative adversarial networks (TimeGAN)cited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Lost in the Non-convex Loss Landscape: How to Fine-tune the Large Time Series Model?cited by 1
  2. 2026Self-Adaptive Scale Handling for Forecasting Time Series with Scale Heterogeneitycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025WaveletDiff: Multilevel Wavelet Diffusion For Time Series Generation
  2. 2025Stage-Diff: Stage-wise Long-Term Time Series Generation Based on Diffusion Models
  3. 2025TSGDiff: Rethinking Synthetic Time Series Generation from a Pure Graph Perspective
  4. 2024Diffusion-TS: Interpretable Diffusion for General Time Series Generation
  5. 2023Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting
  6. 2024Diff-MTS: Temporal-Augmented Conditional Diffusion-based AIGC for Industrial Time Series Towards the Large Model Era
  7. 2026Towards a Unified Generative Model for Scarce Time Series with Domain Experts
  8. 2024Self-Supervised Learning of Time Series Representation via Diffusion Process and Imputation-Interpolation-Forecasting Mask