Multivariate time series classification is a critical problem in data mining with broad applications. It requires harnessing the inter-relationship of multiple variables and various ranges of temporal dependencies to assign the correct classification label of the time series. Multivariate time series may come from a wide range of sources and be used in various scenarios, bringing the classifier challenge of temporal representation learning. We propose a novel convolutional neural network architecture called Attentional Gated Res2Net for multivariate time series classification. Our model uses hierarchical residual-like connections to achieve multi-scale receptive fields and capture multi-granular temporal information. The gating mechanism enables the model to consider the relations between the feature maps extracted by receptive fields of multiple sizes for information fusion. Further, we propose two types of attention modules, channel-wise attention and block-wise attention, to better leverage the multi-granular temporal patterns. Our experimental results on 14 benchmark multivariate time-series datasets show that our model outperforms several baselines and state-of-the-art methods by a large margin. Our model outperforms the SOTA by a large margin, the classification accuracy of our model is 10.16% better than the SOTA model. Besides, we demonstrate that our model improves the performance of existing models when used as a plugin. Further, based on our experiments and analysis, we provide practical advice on applying our model to a new problem.

多元时间序列分类是具有广泛应用的数据挖掘中的关键问题。它需要利用多个变量的相互关系和各种时间依赖性范围来分配时间序列的正确分类标签。多元时间序列可能来自广泛的来源并被用于各种场景，带来了时间表示学习的分类器挑战。我们提出了一种新的卷积神经网络架构，称为 Attentional Gated Res2Net，用于多变量时间序列分类。我们的模型使用分层残差连接来实现多尺度感受野并捕获多粒度时间信息。门控机制使模型能够考虑由多种大小的感受野提取的特征图之间的关系，以进行信息融合。此外，我们提出了两种类型的注意模块，通道注意和块注意，以更好地利用多粒度时间模式。我们在 14 个基准多元时间序列数据集上的实验结果表明，我们的模型大大优于几个基线和最先进的方法。我们的模型大大优于 SOTA，我们模型的分类准确率比 SOTA 模型好 10.16%。此外，我们证明了我们的模型在用作插件时提高了现有模型的性能。此外，基于我们的实验和分析，我们提供了将我们的模型应用于新问题的实用建议。