TimeFlow: An Implicit Neural Representation Approach for Continuous Time Series Modeling
Keywords: Time series, Continuous modeling, Forecasting, Imputation, Implicit Neural Representation
TL;DR: We propose a deep continuous model for time series imputation and forecasting which can handle irregular sampled time series and new samples.
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 Number: 11
Loading