VQ-TR: Vector Quantized Attention for Time Series Forecasting

Kashif Rasul, Umang Gupta, Hena Ghonia, Yuriy Nevmyvaka

Keywords: deep learning, time series forecasting, latent variable models, transformer

TL;DR: A linear transformer using a vector quantized cross attention block for time series forecasting.

Abstract: Modern time series datasets can easily contain hundreds or thousands of temporal time points, however, Transformer based models scale poorly to the size of the sequence length constraining their context size in the seq-to-seq setting. In this work, we introduce VQ-TR which maps large sequences to a discrete set of latents representations as part of the Attention module. This allows us to attend over larger context windows with linear complexity with respect to the sequence length. We compare this method with other competitive deep learning and classical univariate probabilistic models and highlight its performance using both probabilistic and point forecasting metrics on a variety of open datasets from different domains.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning