Time Series Continuous Modeling for Imputation and Forecasting with Implicit Neural Representations
This provides a unified framework for handling real-world time series data issues, though it appears incremental as an adaptation of existing implicit neural representation methods.
The paper tackles time series imputation and forecasting challenges like irregular sampling and missing data by developing a continuous-time model using implicit neural representations with a meta-learning modulation mechanism. It achieves state-of-the-art performance on benchmarks and outperforms other time-continuous models.
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.