提出可解释的多变量时间序列分类新方法，兼顾高精度与决策透明性。
ProtoTSNet: Interpretable Multivariate Time Series Classification With Prototypical Parts
- 基于原型网络改进卷积编码器，用分组卷积捕捉动态模式并量化特征重要性。
- 在UEA 30个数据集上表现最优，优于现有事前可解释方法，媲美非可解释模型。
- 结果对领域专家友好，适合医疗、工业等需可信决策的场景。
时间序列数据在工业和医疗等关键领域广泛应用。在这些领域，算法不仅需要高准确率，还需具备可解释性，因为决策后果重大。本文提出ProtoTSNet，一种针对多变量时间序列分类的可解释新方法，通过大幅改进ProtoPNet架构实现。该方法专为时间序列分析的独特挑战设计，包括捕捉动态模式和处理特征重要性的变化。核心创新在于采用分组卷积的修改版卷积编码器，可预先训练为自编码器，用于保留并量化特征重要性。我们在来自UEA数据集的30个多变量时间序列数据集上评估了该模型，与现有的可解释方法及非可解释基线进行比较。通过全面评估和消融实验，证明本方法在事前可解释方法中性能最佳，同时与非可解释及事后可解释方法相比保持竞争力，为领域专家提供可理解的结果。
原文摘要 · Abstract (English)
Time series data is one of the most popular data modalities in critical domains such as industry and medicine. The demand for algorithms that not only exhibit high accuracy but also offer interpretability is crucial in such fields, as decisions made there bear significant consequences. In this paper, we present ProtoTSNet, a novel approach to interpretable classification of multivariate time series data, through substantial enhancements to the ProtoPNet architecture. Our method is tailored to overcome the unique challenges of time series analysis, including capturing dynamic patterns and handling varying feature significance. Central to our innovation is a modified convolutional encoder utilizing group convolutions, pre-trainable as part of an autoencoder and designed to preserve and quantify feature importance. We evaluated our model on 30 multivariate time series datasets from the UEA archive, comparing our approach with existing explainable methods as well as non-explainable baselines. Through comprehensive evaluation and ablation studies, we demonstrate that our approach achieves the best performance among ante-hoc explainable methods while maintaining competitive performance with non-explainable and post-hoc explainable approaches, providing interpretable results accessible to domain experts.
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。