Discrete Representation Learning for Multivariate Time Series.

Publication Type	Academic Article
Authors	Ajirak M, Elbau I, Solomonov N, Grosenick L
Journal	Proc Eur Signal Process Conf EUSIPCO
Volume	2024
Pagination	1132-1136
Date Published	10/23/2024
ISSN	2219-5491
Abstract	This paper focuses on discrete representation learning for multivariate time series with Gaussian processes. To overcome the challenges inherent in incorporating discrete latent variables into deep learning models, our approach uses a Gumbel-softmax reparameterization trick to address non-differentiability, enabling joint clustering and embedding through learnable discretization of the latent space. The proposed architecture thus enhances interpretability both by estimating a low-dimensional embedding for high dimensional time series and by simultaneously discovering discrete latent states. Empirical assessments on synthetic and real-world fMRI data validate the model's efficacy, showing improved classification results using our representation.
DOI	10.23919/eusipco63174.2024.10715138
PubMed ID	40510730
PubMed Central ID	PMC12162130