Discretizing Continuous Time Series for Imputation with Masked Diffusion Training
The Masked Diffusion Time-series Imputation Model (MDTIM) is proposed, which leverages the training paradigm of masked diffusion model for imputation tasks, and introduces Stochastic Discretization, which maps continuous values to ordinal-aware tokens while preserving continuous dynamics.
Dongbin Kim, Seungyun Lee, Geonwoo Shin et al.
· 0 citations