Tabular datasets are ubiquitous in data science applications. Given their
importance, it seems natural to apply state-of-the-art deep learning algorithms
in order to fully unlock their potential. Here we propose neural network models
that represent tabular time series that can optionally leverage their
hierarchical structure. This results in two architectures for tabular time
series: one for learning representations that is analogous to BERT and can be
pre-trained end-to-end and used in downstream tasks, and one that is akin to
GPT and can be used for generation of realistic synthetic tabular sequences. We
demonstrate our models on two datasets: a synthetic credit card transaction
dataset, where the learned representations are used for fraud detection and
synthetic data generation, and on a real pollution dataset, where the learned
encodings are used to predict atmospheric pollutant concentrations. Code and
data are available at https://github.com/IBM/TabFormer.
Description
[2011.01843] Tabular Transformers for Modeling Multivariate Time Series
%0 Generic
%1 padhi2020tabular
%A Padhi, Inkit
%A Schiff, Yair
%A Melnyk, Igor
%A Rigotti, Mattia
%A Mroueh, Youssef
%A Dognin, Pierre
%A Ross, Jerret
%A Nair, Ravi
%A Altman, Erik
%D 2020
%K multivariate timeseries todo:read transformers
%T Tabular Transformers for Modeling Multivariate Time Series
%U http://arxiv.org/abs/2011.01843
%X Tabular datasets are ubiquitous in data science applications. Given their
importance, it seems natural to apply state-of-the-art deep learning algorithms
in order to fully unlock their potential. Here we propose neural network models
that represent tabular time series that can optionally leverage their
hierarchical structure. This results in two architectures for tabular time
series: one for learning representations that is analogous to BERT and can be
pre-trained end-to-end and used in downstream tasks, and one that is akin to
GPT and can be used for generation of realistic synthetic tabular sequences. We
demonstrate our models on two datasets: a synthetic credit card transaction
dataset, where the learned representations are used for fraud detection and
synthetic data generation, and on a real pollution dataset, where the learned
encodings are used to predict atmospheric pollutant concentrations. Code and
data are available at https://github.com/IBM/TabFormer.
@misc{padhi2020tabular,
abstract = {Tabular datasets are ubiquitous in data science applications. Given their
importance, it seems natural to apply state-of-the-art deep learning algorithms
in order to fully unlock their potential. Here we propose neural network models
that represent tabular time series that can optionally leverage their
hierarchical structure. This results in two architectures for tabular time
series: one for learning representations that is analogous to BERT and can be
pre-trained end-to-end and used in downstream tasks, and one that is akin to
GPT and can be used for generation of realistic synthetic tabular sequences. We
demonstrate our models on two datasets: a synthetic credit card transaction
dataset, where the learned representations are used for fraud detection and
synthetic data generation, and on a real pollution dataset, where the learned
encodings are used to predict atmospheric pollutant concentrations. Code and
data are available at https://github.com/IBM/TabFormer.},
added-at = {2021-11-10T15:47:38.000+0100},
author = {Padhi, Inkit and Schiff, Yair and Melnyk, Igor and Rigotti, Mattia and Mroueh, Youssef and Dognin, Pierre and Ross, Jerret and Nair, Ravi and Altman, Erik},
biburl = {https://www.bibsonomy.org/bibtex/2f1f1fd8c0f6fa9c2a433634e84b9039a/annakrause},
description = {[2011.01843] Tabular Transformers for Modeling Multivariate Time Series},
interhash = {b2c6780b0c914259bebcc86bb340d51f},
intrahash = {f1f1fd8c0f6fa9c2a433634e84b9039a},
keywords = {multivariate timeseries todo:read transformers},
note = {cite arxiv:2011.01843Comment: Accepted to ICASSP, 2021; https://github.com/IBM/TabFormer},
timestamp = {2021-11-10T15:47:38.000+0100},
title = {Tabular Transformers for Modeling Multivariate Time Series},
url = {http://arxiv.org/abs/2011.01843},
year = 2020
}