aiqbench analysis
This research introduces MDTIM, a novel masked diffusion framework designed specifically to address the challenges of time series imputation by separating missing and observed values within distinct representation spaces. By employing stochastic discretization to map continuous data into ordinal-aware tokens while preserving temporal dynamics, the model overcomes limitations in existing methods that either fail to distinguish signal from noise or struggle with complex real-world patterns. The approach demonstrates superior robustness and scalability across diverse benchmarks, offering a significant advancement for reliable time series analysis where missing data is prevalent.
Discretizing Continuous Time Series for Imputation with Masked Diffusion Training
arXiv:2608.19119v1 Announce Type: cross Abstract: Time series imputation is a crucial area for reliable time series analysis, yet it remains challenging due to the complex temporal dynamics and noise of real-world data. Existing approaches, however, exhibit two limitations: missing and observed values are embedded within the same representation space without explicit structural separation, and continuous diffusion-based methods are trained to predict added noise rather than the original signal. To address these, we propose the Masked Diffusion Time-series Imputation Model (MDTIM), which leverages the training paradigm of masked diffusion model for imputation tasks. The MASK token is structurally orthogonal to valid observations, and the model directly predicts the original values, naturally aligning both the representation and the learning objective with the imputation task. To bridge the gap between discrete masked diffusion and the continuous, ordinal nature of time series, we further introduce Stochastic Discretization, which maps continuous values to ordinal-aware tokens while preserving continuous dynamics. Our experiments on diverse benchmarks confirm that MDTIM achieves superior robustness and scalability, consistently outperforming state-of-the-art deterministic and generative baselines across various missing scenarios.
Abstract:Time series imputation is a crucial area for reliable time series analysis, yet it remains challenging due to the complex temporal dynamics and noise of real-world data. Existing approaches, however, exhibit two limitations: missing and observed values are embedded within the same representation space without explicit structural separation, and continuous diffusion-based methods are trained to predict added noise rather than the original signal. To address these, we propose the Masked Diffusion Time-series Imputation Model (MDTIM), which leverages the training paradigm of masked diffusion model for imputation tasks. The MASK token is structurally orthogonal to valid observations, and the model directly predicts the original values, naturally aligning both the representation and the learning objective with the imputation task. To bridge the gap between discrete masked diffusion and the continuous, ordinal nature of time series, we further introduce Stochastic Discretization, which maps continuous values to ordinal-aware tokens while preserving continuous dynamics. Our experiments on diverse benchmarks confirm that MDTIM achieves superior robustness and scalability, consistently outperforming state-of-the-art deterministic and generative baselines across various missing scenarios.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
I.2.6; I.5.4; G.3
arXiv:2608.19119 [cs.LG]
(or arXiv:2608.19119v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2608.19119 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 273 words
Related coverage
Latent Laplace Diffusion for Irregular Multivariate Time Series
arXiv · Jun 3, 2026
Informative Missingness to Generate Irregular Clinical Time Series
arXiv · Jun 17, 2026
HALO: Enhancing Time Series Generation via Hyperspherical Latents and Masked AutoregRessive Modeling
arXiv · Sep 29, 2026
UniGIO: Unified Generative Global In-situ Weather Modeling from Spatiotemporal Incomplete Observations
arXiv · Sep 22, 2026