ProtoTSNet: Interpretable Multivariate Time Series Classification With Prototypical Parts

TL;DR

ProtoTSNet is an interpretable multivariate time series classification model that enhances the ProtoPNet architecture with a specialized convolutional encoder, achieving high accuracy and interpretability in critical domains.

Contribution

It introduces a novel, interpretable classification method for multivariate time series using a modified ProtoPNet with group convolutions and autoencoder pre-training.

Findings

Achieves top performance among ante-hoc explainable methods

Maintains competitive accuracy with non-explainable models

Provides interpretable results suitable for domain experts

Abstract

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.