Time Series Continuous Modeling for Imputation and Forecasting with Implicit Neural Representations

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

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.

Submission Length: Regular submission (no more than 12 pages of main content)

Changes Since Last Submission: Reference to Appendix H in the meta-learning explanation (Section 3.2.)

Code: https://github.com/EtienneLnr/TimeFlow.git

Assigned Action Editor: ~Yingnian_Wu1

Submission Number: 2117