Learning Interpretable Neural Discrete Representation for Time Series Classification

Etienne Le Naour, Ghislain Agoua, Nicolas Baskiotis, Vincent GuigueICLR 2023 · OpenReview

Abstract

Time series classification is a challenging research field with many real-life applications. Recent advances in deep learning have significantly improved the state of the art: recurrent or convolutional architectures allow automatic extraction of complex discriminating patterns that improve performance. Those approaches suffer from a lack of interpretability: the patterns are mapped into a high dimensional latent vector space, they are not representable in the time domain, and are often even not localizable. In this paper, we present a novel neural convolutional architecture that aims to provide a trade-off between interpretability and effectiveness based on the learning of a dictionary of discrete representations. The proposed model guarantees (1) that a small number of patterns are learned, and they are visualizable and interpretable (2) a shift equivariance property of the model associated with a time-consistency of the representation (3) a linear classifier over a limited number of patterns leading to an explainable decision. To ensure the robustness of the discrete representation, they are learned in an unsupervised process independently of the classification task. This allows further great performances in transfer learning. We present extensive experiments on the UCR benchmark wrt usual baselines. The interpretability of the model is illustrated empirically. The chosen trade-off results obviously in a decrease in performance compared to the state of the art. The performance drop is however limited and very dependent on the application domain. The experiments highlight the efficiency of the model for the transfer learning task, showing the robustness of the representations.
BibTeX
@inproceedings{naour2023learning,
  author = {Etienne Le Naour and Ghislain Agoua and Nicolas Baskiotis and Vincent Guigue},
  title = {{Learning Interpretable Neural Discrete Representation for Time Series Classification}},
  booktitle = {International Conference on Learning Representations},
  year = {2023},
  url = {https://openreview.net/forum?id=XkYe7K_AQ8I},
}

Loading related content...

Figure