Generalised Interpretable Shapelets for Irregular Time Series
arXiv:2005.13948
Abstract
The shapelet transform is a form of feature extraction for time series, in which a time series is described by its similarity to each of a collection of `shapelets'. However it has previously suffered from a number of limitations, such as being limited to regularly-spaced fully-observed time series, and having to choose between efficient training and interpretability. Here, we extend the method to continuous time, and in doing so handle the general case of irregularly-sampled partially-observed multivariate time series. Furthermore, we show that a simple regularisation penalty may be used to train efficiently without sacrificing interpretability. The continuous-time formulation additionally allows for learning the length of each shapelet (previously a discrete object) in a differentiable manner. Finally, we demonstrate that the measure of similarity between time series may be generalised to a learnt pseudometric. We validate our method by demonstrating its performance and interpretability on several datasets; for example we discover (purely from data) that the digits 5 and 6 may be distinguished by the chirality of their bottom loop, and that a kind of spectral gap exists in spoken audio classification.
References in corpus (10)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition
- The UEA multivariate time series classification archive, 2018
- Ultra-Fast Shapelets for Time Series Classification
- Signatory: differentiable computations of the signature and logsignature transforms, on both CPU and GPU
- A scalable end-to-end Gaussian process adapter for irregularly sampled time series classification
- The Great Time Series Classification Bake Off: An Experimental Evaluation of Recently Proposed Algorithms. Extended Version
- Learning stochastic differential equations using RNN with log signature features
- Interpolation-Prediction Networks for Irregularly Sampled Time Series
- Learning Interpretable Shapelets for Time Series Classification through Adversarial Regularization