用连续建模构建时间序列填补基础模型，支持多种缺失模式。
MoTM: Towards a Foundation Model for Time Series Imputation based on Continuous Modeling
- 将时间序列视为连续函数，通过混合神经表示建模
- 在不同缺失场景下均表现稳健，跨分布泛化能力强
- 适合需要灵活处理缺失数据的工业级时序系统
近年来，时间序列基础模型受到广泛关注，但对跨域缺失值填补这一关键任务仍研究不足。本文提出首个基于连续建模的时间序列填补基础模型——MoTM（Mixture of Timeflow Models）。利用隐式神经表示（INRs）将时间序列建模为连续函数，天然适应不同缺失模式与采样率。针对INRs在分布偏移下性能下降的问题，MoTM结合一组独立训练于不同时间序列家族的INR基函数，以及一个在推理时根据观测上下文自适应的岭回归器。实验表明，该模型在多种填补场景（如块状、点状缺失，可变采样率）中均展现出强鲁棒性与跨域泛化能力，为可适配的时间序列填补基础模型提供了新路径。
原文摘要 · Abstract (English)
Recent years have witnessed a growing interest for time series foundation models, with a strong emphasis on the forecasting task. Yet, the crucial task of out-of-domain imputation of missing values remains largely underexplored. We propose a first step to fill this gap by leveraging implicit neural representations (INRs). INRs model time series as continuous functions and naturally handle various missing data scenarios and sampling rates. While they have shown strong performance within specific distributions, they struggle under distribution shifts. To address this, we introduce MoTM (Mixture of Timeflow Models), a step toward a foundation model for time series imputation. Building on the idea that a new time series is a mixture of previously seen patterns, MoTM combines a basis of INRs, each trained independently on a distinct family of time series, with a ridge regressor that adapts to the observed context at inference. We demonstrate robust in-domain and out-of-domain generalization across diverse imputation scenarios (e.g., block and pointwise missingness, variable sampling rates), paving the way for adaptable foundation imputation models.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。