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

TL;DR

This paper presents a continuous-time neural modeling approach for time series imputation and forecasting, effectively handling irregular, missing, or unaligned data, and achieving state-of-the-art results.

Contribution

It introduces a novel implicit neural representation-based model with meta-learning adaptation for improved time series imputation and forecasting.

Findings

Achieves state-of-the-art performance on classical benchmarks.

Effectively handles irregular and missing data scenarios.

Outperforms alternative continuous-time models.

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.