Deep neural networks, including transformers and convolutional neural networks, have significantly improved multivariate time series classification (MTSC). However, these methods often rely on supervised learning, which does not fully account for the sparsity and locality of patterns in time series data (e.g., diseases-related anomalous points in ECG). To address this challenge, we formally reformulate MTSC as a weakly supervised problem, introducing a novel multiple-instance learning (MIL) framework for better localization of patterns of interest and modeling time dependencies within time series. Our novel approach, TimeMIL, formulates the temporal correlation and ordering within a time-aware MIL pooling, leveraging a tokenized transformer with a specialized learnable wavelet positional token. The proposed method surpassed 26 recent state-of-the-art methods, underscoring the effectiveness of the weakly supervised TimeMIL in MTSC. The code will be available at https://github.com/xiwenc1/TimeMIL.

翻译：深度神经网络，包括Transformer和卷积神经网络，已显著提升了多元时间序列分类的性能。然而，这些方法通常依赖于监督学习，未能充分考虑时间序列数据中模式的稀疏性和局部性（例如，心电图中与疾病相关的异常点）。为应对这一挑战，我们正式将多元时间序列分类重新表述为一个弱监督问题，引入了一种新颖的多示例学习框架，以更好地定位感兴趣的模式并建模时间序列内部的时间依赖性。我们提出的新方法TimeMIL，通过一种时间感知的多示例学习池化操作来建模时间相关性和顺序性，并利用一个具有专用可学习小波位置标记的标记化Transformer。所提出的方法超越了26种近期最先进的方法，突显了弱监督TimeMIL在多元时间序列分类中的有效性。代码将在 https://github.com/xiwenc1/TimeMIL 提供。