Time series imputation remains a significant challenge across many fields due to the potentially significant variability in the type of data being modelled. Whilst traditional imputation methods often impose strong assumptions on the underlying data generation process, limiting their applicability, researchers have recently begun to investigate the potential of deep learning for this task, inspired by the strong performance shown by these models in both classification and regression problems across a range of applications. In this work we propose MADS, a novel auto-decoding framework for time series imputation, built upon implicit neural representations. Our method leverages the capabilities of SIRENs for high fidelity reconstruction of signals and irregular data, and combines it with a hypernetwork architecture which allows us to generalise by learning a prior over the space of time series. We evaluate our model on two real-world datasets, and show that it outperforms state-of-the-art methods for time series imputation. On the human activity dataset, it improves imputation performance by at least 40%, while on the air quality dataset it is shown to be competitive across all metrics. When evaluated on synthetic data, our model results in the best average rank across different dataset configurations over all baselines.

翻译：时间序列插补仍是众多领域中面临的重大挑战，原因在于被建模数据类型存在显著变异性。传统插补方法通常对数据生成过程施加较强假设，限制了其适用性。受深度学习模型在各类分类与回归问题中展现的卓越性能启发，研究者近期开始探索该技术在此任务中的潜力。本文提出MADS——一种基于隐式神经表征的新型自解码时间序列插补框架。该方法利用SIREN对高保真信号重建和不规则数据的处理能力，结合超网络架构通过在学习时间序列空间先验实现泛化。我们在两个真实世界数据集上评估模型，证明其优于现有最优时间序列插补方法：在人类活动数据集上插补性能提升至少40%，在空气质量数据集上所有指标均具竞争力。在合成数据评估中，本模型在所有基线方法中针对不同数据集配置取得最优平均排名。