Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Workshop on Learning from Time Series for Health

TimeFlow: An Implicit Neural Representation Approach for Continuous Time Series Modeling

Etienne Le Naour · Louis Serrano · Léon Migus · Yuan Yin · Ghislain Agoua · Nicolas Baskiotis · patrick Gallinari · Vincent Guigue

Keywords: [ time series ] [ forecasting ] [ Imputation ] [ Implicit Neural Representation ] [ Continuous modeling ]


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.

Chat is not available.