提出连续线性位置编码，提升非均匀采样时间序列预测效果
Continuous-Time Linear Positional Embedding for Irregular Time Series Forecasting
- 用连续线性函数替代传统位置编码，动态建模时间位置信息
- 在多个非均匀采样数据集上超越现有方法，最高提升6.2%准确率
- 特别适合医疗、金融等真实世界中不规则采样场景
非均匀采样时间序列预测在实际应用中普遍存在，但以往研究多集中于均匀采样场景，通常依赖Transformer架构。为将Transformer扩展至处理非均匀时间序列，本文聚焦于位置编码这一表征时间信息的核心组件。提出连续时间线性位置编码（CTLPE），通过学习一个连续线性函数来编码时间信息，有效解决观测模式不一致与时间间隔不规则两大挑战。实验表明，基于神经控制微分方程学习的连续位置编码中，线性函数表现优于其他连续形式，且其性质符合理想位置编码理论要求。在多个非均匀采样时间序列数据集上，CTLPE均显著优于现有方法，验证了其有效性。
原文摘要 · Abstract (English)
Irregularly sampled time series forecasting, characterized by non-uniform intervals, is prevalent in practical applications. However, previous research have been focused on regular time series forecasting, typically relying on transformer architectures. To extend transformers to handle irregular time series, we tackle the positional embedding which represents the temporal information of the data. We propose CTLPE, a method learning a continuous linear function for encoding temporal information. The two challenges of irregular time series, inconsistent observation patterns and irregular time gaps, are solved by learning a continuous-time function and concise representation of position. Additionally, the linear continuous function is empirically shown superior to other continuous functions by learning a neural controlled differential equation-based positional embedding, and theoretically supported with properties of ideal positional embedding. CTLPE outperforms existing techniques across various irregularly-sampled time series datasets, showcasing its enhanced efficacy.
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。