不规则采样多元时间序列的兼容Transformer
Compatible Transformer for Irregularly Sampled Multivariate Time Series
AI总结：
针对不规则采样多元时间序列，提出基于变量内/变量间注意力的Transformer编码器CoFormer，以学习样本级时间交互表示，在分类和预测等下游任务上显著优于现有方法。
摘要：
为了分析多元时间序列，大多数先前的方法假设时间序列是规则采样的，即连续测量之间的间隔保持不变。实际上，由于传感器故障和干预，数据采集系统可能会产生不规则采样的时间序列。因此，为规则采样多元时间序列设计的方法无法直接处理不规则采样问题，因为沿时间维度和变量维度都存在缺失。为了填补这一空白，我们提出了一种基于Transformer的编码器CoFormer，用于学习不规则采样多元时间序列中每个样本的全面时间交互表示。在CoFormer中，我们将每个样本视为一个唯一的变量时间点，并利用变量内/变量间注意力机制，基于变量内/变量间关系学习样本级的时间/交互表示。以CoFormer为核心，我们可以分析不规则采样的多元时间序列以完成许多下游任务，包括分类和预测。我们在3个真实世界数据集上进行了广泛实验，验证了所提出的CoFormer显著且一致地优于现有方法。
英文摘要：
To analyze multivariate time series, most previous methods assume regular subsampling of time series, where the interval between adjacent measurements and the number of samples remain unchanged. Practically, data collection systems could produce irregularly sampled time series due to sensor failures and interventions. However, existing methods designed for regularly sampled multivariate time series cannot directly handle irregularity owing to misalignment along both temporal and variate dimensions. To fill this gap, we propose Compatible Transformer (CoFormer), a transformer-based encoder to achieve comprehensive temporal-interaction feature learning for each individual sample in irregular multivariate time series. In CoFormer, we view each sample as a unique variate-time point and leverage intra-variate/inter-variate attentions to learn sample-wise temporal/interaction features based on intra-variate/inter-variate neighbors. With CoFormer as the core, we can analyze irregularly sampled multivariate time series for many downstream tasks, including classification and prediction. We conduct extensive experiments on 3 real-world datasets and validate that the proposed CoFormer significantly and consistently outperforms existing methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
