FlexTSF可直接处理不规则时间序列，无需补全数据
FlexTSF: A Flexible Forecasting Model for Time Series with Variable Regularities
- 用微分方程建模时间间隔，天然支持不等距采样
- 在16个数据集上超越现有模型，零样本迁移表现最优
- 适合传感器、医疗等真实场景中的不规则时序预测
具有不规则时间结构的时间序列预测对通用预训练模型仍是挑战。现有方法常假设规则采样或严重依赖插补，限制了在真实场景中的应用，因传感设备和记录方式多样导致不规则性普遍存在。我们提出FlexTSF，一种专为具有可变时间规律的时间序列设计的灵活预测模型。其核心是IVP Patcher，一种基于初值问题（IVPs）的连续时间分块模块，能天然支持不等距时间间隔、可变序列长度和缺失值。FlexTSF采用解码器仅架构，通过特殊因果自注意力机制融合归一化时间戳输入与领域特定统计量，实现跨领域的适应性。在16个数据集上的大量实验表明，FlexTSF在经典预测任务、零样本泛化及低资源微调条件下均显著优于现有模型。消融研究证实各设计组件的贡献，且不依赖预设固定分块长度的优势。
原文摘要 · Abstract (English)
Forecasting time series with irregular temporal structures remains challenging for universal pre-trained models. Existing approaches often assume regular sampling or depend heavily on imputation, limiting their applicability in real-world scenarios where irregularities are prevalent due to diverse sensing devices and recording practices. We introduce FlexTSF, a flexible forecasting model specifically designed for time series data with variable temporal regularities. At its foundation lies the IVP Patcher, a continuous-time patching module leveraging Initial Value Problems (IVPs) to inherently support uneven time intervals, variable sequence lengths, and missing values. FlexTSF employs a decoder-only architecture that integrates normalized timestamp inputs and domain-specific statistics through a specialized causal self-attention mechanism, enabling adaptability across domains. Extensive experiments on 16 datasets demonstrate FlexTSF's effectiveness, significantly outperforming existing models in classic forecasting scenarios, zero-shot generalization, and low-resource fine-tuning conditions. Ablation studies confirm the contributions of each design component and the advantage of not relying on predefined fixed patch lengths.
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。