Unsupervised Scalable Representation Learning for Multivariate Time Series

Unsupervised Scalable Representation Learning for Multivariate Time Series. Franceschi, J., Dieuleveut, A., & Jaggi, M. arXiv:1901.10738 [cs, stat], January, 2020. arXiv: 1901.10738

Paper abstract bibtex

Time series constitute a challenging data type for machine learning algorithms, due to their highly variable lengths and sparse labeling in practice. In this paper, we tackle this challenge by proposing an unsupervised method to learn universal embeddings of time series. Unlike previous works, it is scalable with respect to their length and we demonstrate the quality, transferability and practicability of the learned representations with thorough experiments and comparisons. To this end, we combine an encoder based on causal dilated convolutions with a novel triplet loss employing time-based negative sampling, obtaining general-purpose representations for variable length and multivariate time series.

@article{franceschi_unsupervised_2020,
	title = {Unsupervised {Scalable} {Representation} {Learning} for {Multivariate} {Time} {Series}},
	url = {http://arxiv.org/abs/1901.10738},
	abstract = {Time series constitute a challenging data type for machine learning algorithms, due to their highly variable lengths and sparse labeling in practice. In this paper, we tackle this challenge by proposing an unsupervised method to learn universal embeddings of time series. Unlike previous works, it is scalable with respect to their length and we demonstrate the quality, transferability and practicability of the learned representations with thorough experiments and comparisons. To this end, we combine an encoder based on causal dilated convolutions with a novel triplet loss employing time-based negative sampling, obtaining general-purpose representations for variable length and multivariate time series.},
	urldate = {2020-07-20},
	journal = {arXiv:1901.10738 [cs, stat]},
	author = {Franceschi, Jean-Yves and Dieuleveut, Aymeric and Jaggi, Martin},
	month = jan,
	year = {2020},
	note = {arXiv: 1901.10738},
	keywords = {Computer Science - Machine Learning, Computer Science - Neural and Evolutionary Computing, Statistics - Machine Learning},
}

Downloads: 0

{"_id":"AxSDRT8bx4fmEJWti","bibbaseid":"franceschi-dieuleveut-jaggi-unsupervisedscalablerepresentationlearningformultivariatetimeseries-2020","author_short":["Franceschi, J.","Dieuleveut, A.","Jaggi, M."],"bibdata":{"bibtype":"article","type":"article","title":"Unsupervised Scalable Representation Learning for Multivariate Time Series","url":"http://arxiv.org/abs/1901.10738","abstract":"Time series constitute a challenging data type for machine learning algorithms, due to their highly variable lengths and sparse labeling in practice. In this paper, we tackle this challenge by proposing an unsupervised method to learn universal embeddings of time series. Unlike previous works, it is scalable with respect to their length and we demonstrate the quality, transferability and practicability of the learned representations with thorough experiments and comparisons. To this end, we combine an encoder based on causal dilated convolutions with a novel triplet loss employing time-based negative sampling, obtaining general-purpose representations for variable length and multivariate time series.","urldate":"2020-07-20","journal":"arXiv:1901.10738 [cs, stat]","author":[{"propositions":[],"lastnames":["Franceschi"],"firstnames":["Jean-Yves"],"suffixes":[]},{"propositions":[],"lastnames":["Dieuleveut"],"firstnames":["Aymeric"],"suffixes":[]},{"propositions":[],"lastnames":["Jaggi"],"firstnames":["Martin"],"suffixes":[]}],"month":"January","year":"2020","note":"arXiv: 1901.10738","keywords":"Computer Science - Machine Learning, Computer Science - Neural and Evolutionary Computing, Statistics - Machine Learning","bibtex":"@article{franceschi_unsupervised_2020,\n\ttitle = {Unsupervised {Scalable} {Representation} {Learning} for {Multivariate} {Time} {Series}},\n\turl = {http://arxiv.org/abs/1901.10738},\n\tabstract = {Time series constitute a challenging data type for machine learning algorithms, due to their highly variable lengths and sparse labeling in practice. In this paper, we tackle this challenge by proposing an unsupervised method to learn universal embeddings of time series. Unlike previous works, it is scalable with respect to their length and we demonstrate the quality, transferability and practicability of the learned representations with thorough experiments and comparisons. To this end, we combine an encoder based on causal dilated convolutions with a novel triplet loss employing time-based negative sampling, obtaining general-purpose representations for variable length and multivariate time series.},\n\turldate = {2020-07-20},\n\tjournal = {arXiv:1901.10738 [cs, stat]},\n\tauthor = {Franceschi, Jean-Yves and Dieuleveut, Aymeric and Jaggi, Martin},\n\tmonth = jan,\n\tyear = {2020},\n\tnote = {arXiv: 1901.10738},\n\tkeywords = {Computer Science - Machine Learning, Computer Science - Neural and Evolutionary Computing, Statistics - Machine Learning},\n}\n","author_short":["Franceschi, J.","Dieuleveut, A.","Jaggi, M."],"key":"franceschi_unsupervised_2020","id":"franceschi_unsupervised_2020","bibbaseid":"franceschi-dieuleveut-jaggi-unsupervisedscalablerepresentationlearningformultivariatetimeseries-2020","role":"author","urls":{"Paper":"http://arxiv.org/abs/1901.10738"},"keyword":["Computer Science - Machine Learning","Computer Science - Neural and Evolutionary Computing","Statistics - Machine Learning"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/mh_lenguyen","dataSources":["yanwtMpCcFaHzRwWb","iwKepCrWBps7ojhDx"],"keywords":["computer science - machine learning","computer science - neural and evolutionary computing","statistics - machine learning"],"search_terms":["unsupervised","scalable","representation","learning","multivariate","time","series","franceschi","dieuleveut","jaggi"],"title":"Unsupervised Scalable Representation Learning for Multivariate Time Series","year":2020}