U-Former ODE: Fast Probabilistic Forecasting of Irregular Time Series
Probabilistic forecasting of irregularly sampled time series is crucial in domains such as healthcare and finance, yet it remains a formidable challenge. Existing Neural Controlled Differential Equation (Neural CDE) approaches, while effective at modelling continuous dynamics, suffer from slow, inherently sequential computation, which restricts scalability and limits access to global context. We introduce UFO (U-Former ODE), a novel architecture that seamlessly integrates the parallelizable, multiscale feature extraction of U-Nets, the powerful global modelling of Transformers, and the continuous-time dynamics of Neural CDEs. By constructing a fully causal, parallelizable model, UFO achieves a global receptive field while retaining strong sensitivity to local temporal dynamics. Extensive experiments on five standard benchmarks -- covering both regularly and irregularly sampled time series -- demonstrate that UFO consistently outperforms ten state-of-the-art neural baselines in predictive accuracy. Moreover, UFO delivers up to 15$\times$ faster inference compared to conventional Neural CDEs, with consistently strong performance on long and highly multivariate sequences.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Probabilistic Circuits for Irregular Multivariate Time Series Forecasting
Joint probabilistic modeling is essential for forecasting irregular multivariate time series (IMTS) to accurately quantify uncertainty. Existing approaches often struggle to balance model expressivity with consistent mar…
Multivariate Time Series ForecastingDensity EstimationProbabilistic Forecasting of Irregular Time Series via Conditional Flows
Probabilistic forecasting of irregularly sampled multivariate time series with missing values is an important problem in many fields, including health care, astronomy, and climate. State-of-the-art methods for the task e…
AstronomyIrregular Time SeriesMissing ValuesTime SeriesProbabilistic NDVI Forecasting from Sparse Satellite Time Series and Weather Covariates
Short-term forecasting of vegetation dynamics is a key enabler for data-driven decision support in precision agriculture. Normalized Difference Vegetation Index (NDVI) forecasting from satellite observations, however, re…
Feature EngineeringContinuous-Time Linear Positional Embedding for Irregular Time Series Forecasting
Irregularly sampled time series forecasting, characterized by non-uniform intervals, is prevalent in practical applications. However, previous research have been focused on regular time series forecasting, typically rely…
Irregular Time SeriesTime SeriesTime Series ForecastingTS-ICL: A Flexible Time-Indexed Foundation Model for Time Series via In-Context Learning
Foundation models mark a profound paradigm shift in time series modeling, with task-specific models being superseded by general-purpose zero-shot models. Yet, current approaches primarily focus on forecasting, while real…