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.

翻译：我们提出了一种面向时序数据插补与预测的新型建模方法，旨在解决实际数据中常见的挑战，例如非规则采样、数据缺失或多传感器测量不同步等问题。该方法基于连续时间依赖的序列演化动力学模型，通过改进的条件隐式神经表示实现序贯数据建模。一种由元学习算法驱动的调制机制，使模型能够自适应未见样本并在观测时间窗口外进行长期预测外推。该模型为涵盖多种复杂场景的插补与预测任务提供了高度灵活且统一的框架，在经典基准测试中达到了最先进的性能，并优于其他连续时间模型。