用注意力引导的微分方程模型，更好处理时间序列中的缺失数据。
TANDEM: Temporal Attention-guided Neural Differential Equations for Missingness in Time Series Classification
- 通过注意力机制融合观测值、插值路径和连续隐状态
- 在30个基准数据集和真实医疗数据上超越现有方法
- 适合需要精准建模时间动态的医疗、金融等场景
时间序列分类中的缺失数据处理仍是多个领域的重大挑战。传统方法依赖插补，可能引入偏差或无法捕捉潜在时序动态。本文提出TANDEM（Temporal Attention-guided Neural Differential Equations for Missingness），一种基于注意力引导的神经微分方程框架，用于对含缺失值的时间序列进行有效分类。该方法通过新型注意力机制，整合原始观测、插值控制路径与连续隐动态，使模型聚焦于数据中最关键的信息。我们在30个基准数据集和一个真实医疗数据集上评估TANDEM，结果表明其显著优于现有最先进方法。该框架不仅提升分类准确率，还为缺失数据处理提供新思路，具有实际应用价值。
原文摘要 · Abstract (English)
Handling missing data in time series classification remains a significant challenge in various domains. Traditional methods often rely on imputation, which may introduce bias or fail to capture the underlying temporal dynamics. In this paper, we propose TANDEM (Temporal Attention-guided Neural Differential Equations for Missingness), an attention-guided neural differential equation framework that effectively classifies time series data with missing values. Our approach integrates raw observation, interpolated control path, and continuous latent dynamics through a novel attention mechanism, allowing the model to focus on the most informative aspects of the data. We evaluate TANDEM on 30 benchmark datasets and a real-world medical dataset, demonstrating its superiority over existing state-of-the-art methods. Our framework not only improves classification accuracy but also provides insights into the handling of missing data, making it a valuable tool in practice.
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。