Irregularly-sampled time series (ITS) are native to high-impact domains like healthcare, where measurements are collected over time at uneven intervals. However, for many classification problems, only small portions of long time series are often relevant to the class label. In this case, existing ITS models often fail to classify long series since they rely on careful imputation, which easily over- or under-samples the relevant regions. Using this insight, we then propose CAT, a model that classifies multivariate ITS by explicitly seeking highly-relevant portions of an input series' timeline. CAT achieves this by integrating three components: (1) A Moment Network learns to seek relevant moments in an ITS's continuous timeline using reinforcement learning. (2) A Receptor Network models the temporal dynamics of both observations and their timing localized around predicted moments. (3) A recurrent Transition Model models the sequence of transitions between these moments, cultivating a representation with which the series is classified. Using synthetic and real data, we find that CAT outperforms ten state-of-the-art methods by finding short signals in long irregular time series.

翻译：不规则采样的时间序列（ITS）天然存在于医疗等具有高影响力的领域，这些领域中测量值以不均匀的时间间隔收集。然而，对于许多分类问题，长时间序列中通常只有小部分与类别标签相关。在这种情况下，现有的ITS模型往往难以对长序列进行分类，因为它们依赖于精细的数据插补，而这容易对相关区域进行过采样或欠采样。基于这一洞察，我们提出了CAT模型，该模型通过显式搜索输入序列时间线上高度相关的部分来对多元ITS进行分类。CAT通过整合三个组件实现这一目标：（1）时刻网络利用强化学习学习在ITS的连续时间线上搜索相关时刻。（2）受体网络对观测值及其预测时刻附近的局部时间动态进行建模。（3）循环转换模型对这些时刻之间的转换序列进行建模，从而培养出用于序列分类的表示。通过合成数据和真实数据，我们发现CAT通过在长不规则时间序列中找到短信号，其表现优于十种最先进的方法。