Tabular Transformers for Modeling Multivariate Time Series
Authors:
Preprint
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.Keywords
All Related Versions
This publication has 5 references indexed in Scilit:
- TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data2020
- BioBERT: a pre-trained biomedical language representation model for biomedical text miningBioinformatics, 2019
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding2019
- HIBERT: Document Level Pre-training of Hierarchical Bidirectional Transformers for Document Summarization2019
- Assessing Beijing's PM 2.5 pollution: severity, weather impact, APEC and winter heatingProceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2015