Learnable Group Transform For Time-Series

Romain Cosentino, Behnaam Aazhang
Proceedings of the 37th International Conference on Machine Learning, PMLR 119:2164-2173, 2020.

Abstract

We propose a novel approach to filter bank learning for time-series by considering spectral decompositions of signals defined as a Group Transform. This framework allows us to generalize classical time-frequency transformations such as the Wavelet Transform, and to efficiently learn the representation of signals. While the creation of the wavelet transform filter-bank relies on affine transformations of a mother filter, our approach allows for non-linear transformations. The transformations induced by such maps enable us to span a larger class of signal representations, from wavelet to chirplet-like filters. We propose a parameterization of such a non-linear map such that its sampling can be optimized for a specific task and signal. The Learnable Group Transform can be cast into a Deep Neural Network. The experiments on diverse time-series datasets demonstrate the expressivity of this framework, which competes with state-of-the-art performances.

Cite this Paper

BibTeX
@InProceedings{pmlr-v119-cosentino20a, title = {Learnable Group Transform For Time-Series}, author = {Cosentino, Romain and Aazhang, Behnaam}, booktitle = {Proceedings of the 37th International Conference on Machine Learning}, pages = {2164--2173}, year = {2020}, editor = {III, Hal Daumé and Singh, Aarti}, volume = {119}, series = {Proceedings of Machine Learning Research}, month = {13--18 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v119/cosentino20a/cosentino20a.pdf}, url = {https://proceedings.mlr.press/v119/cosentino20a.html}, abstract = {We propose a novel approach to filter bank learning for time-series by considering spectral decompositions of signals defined as a Group Transform. This framework allows us to generalize classical time-frequency transformations such as the Wavelet Transform, and to efficiently learn the representation of signals. While the creation of the wavelet transform filter-bank relies on affine transformations of a mother filter, our approach allows for non-linear transformations. The transformations induced by such maps enable us to span a larger class of signal representations, from wavelet to chirplet-like filters. We propose a parameterization of such a non-linear map such that its sampling can be optimized for a specific task and signal. The Learnable Group Transform can be cast into a Deep Neural Network. The experiments on diverse time-series datasets demonstrate the expressivity of this framework, which competes with state-of-the-art performances.} }
Endnote
%0 Conference Paper %T Learnable Group Transform For Time-Series %A Romain Cosentino %A Behnaam Aazhang %B Proceedings of the 37th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2020 %E Hal Daumé III %E Aarti Singh %F pmlr-v119-cosentino20a %I PMLR %P 2164--2173 %U https://proceedings.mlr.press/v119/cosentino20a.html %V 119 %X We propose a novel approach to filter bank learning for time-series by considering spectral decompositions of signals defined as a Group Transform. This framework allows us to generalize classical time-frequency transformations such as the Wavelet Transform, and to efficiently learn the representation of signals. While the creation of the wavelet transform filter-bank relies on affine transformations of a mother filter, our approach allows for non-linear transformations. The transformations induced by such maps enable us to span a larger class of signal representations, from wavelet to chirplet-like filters. We propose a parameterization of such a non-linear map such that its sampling can be optimized for a specific task and signal. The Learnable Group Transform can be cast into a Deep Neural Network. The experiments on diverse time-series datasets demonstrate the expressivity of this framework, which competes with state-of-the-art performances.
APA
Cosentino, R. & Aazhang, B.. (2020). Learnable Group Transform For Time-Series. Proceedings of the 37th International Conference on Machine Learning, in Proceedings of Machine Learning Research 119:2164-2173 Available from https://proceedings.mlr.press/v119/cosentino20a.html.

Related Material