Time Series Continuous Modeling for Imputation and Forecasting with Implicit Neural Representations
Abstract
We introduce a novel modeling approach for time series imputation and forecasting, tailored to address the challenges often encountered in real-world data, such as irregular samples, missing data, or unaligned measurements from multiple sensors. Our method relies on a continuous-time-dependent model of the series' evolution dynamics. It leverages adaptations of conditional, implicit neural representations for sequential data. A modulation mechanism, driven by a meta-learning algorithm, allows adaptation to unseen samples and extrapolation beyond observed time-windows for long-term predictions. The model provides a highly flexible and unified framework for imputation and forecasting tasks across a wide range of challenging scenarios. It achieves state-of-the-art performance on classical benchmarks and outperforms alternative time-continuous models.
Cite
@article{arxiv.2306.05880,
title = {Time Series Continuous Modeling for Imputation and Forecasting with Implicit Neural Representations},
author = {Etienne Le Naour and Louis Serrano and Léon Migus and Yuan Yin and Ghislain Agoua and Nicolas Baskiotis and Patrick Gallinari and Vincent Guigue},
journal= {arXiv preprint arXiv:2306.05880},
year = {2026}
}