# Bidirectional Generative Pre-training for Improving Healthcare Time-series Representation Learning

arXiv: https://arxiv.org/abs/2402.09558 · HTML: https://mlsanity.com/paper/2402.09558/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 47 references that are in the map.
- First posted on arXiv 14 Feb 2024.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting](https://mlsanity.com/paper/2201.12740/) (2022)
- [Retentive Network: A Successor to Transformer for Large Language Models](https://mlsanity.com/paper/2307.08621/) (2023)
- [Recurrent Neural Networks for Multivariate Time Series with Missing Values](https://mlsanity.com/paper/1606.01865/) (2016)
- [TS2Vec: Towards Universal Representation of Time Series](https://mlsanity.com/paper/2106.10466/) (2021)
- [A Transformer-based Framework for Multivariate Time Series Representation Learning](https://mlsanity.com/paper/2010.02803/) (2020)
- [Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth](https://mlsanity.com/paper/2103.03404/) (2021)
- [Time-Series Representation Learning via Temporal and Contextual Contrasting](https://mlsanity.com/paper/2106.14112/) (2021)
- [Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency](https://mlsanity.com/paper/2206.08496/) (2022)
- [Multi-Time Attention Networks for Irregularly Sampled Time Series](https://mlsanity.com/paper/2101.10318/) (2021)
- [Set Functions for Time Series](https://mlsanity.com/paper/1909.12064/) (2019)
- [A Length-Extrapolatable Transformer](https://mlsanity.com/paper/2212.10554/) (2022)
- [Graph-Guided Network for Irregularly Sampled Multivariate Time Series](https://mlsanity.com/paper/2110.05357/) (2021)
- [Low-Rank Bottleneck in Multi-head Attention Models](https://mlsanity.com/paper/2002.07028/) (2020)
- [XSleepNet: Multi-View Sequential Model for Automatic Sleep Staging](https://mlsanity.com/paper/2007.05492/) (2020)
- [Self-Supervised Time Series Representation Learning via Cross Reconstruction Transformer](https://mlsanity.com/paper/2205.09928/) (2022)
- [TROIKA: A General Framework for Heart Rate Monitoring Using Wrist-Type Photoplethysmographic Signals During Intensive Physical Exercise](https://mlsanity.com/paper/1409.5181/) (2014)

## Built on by (most cited first, 2 of 2)

- [TrajGPT: Irregular Time-Series Representation Learning for Health Trajectory Analysis](https://mlsanity.com/paper/2410.02133/) (2024)
- [Enhancing Electrocardiogram Signal Analysis Using NLP-Inspired Techniques: A Novel Approach with Embedding and Self-Attention](https://mlsanity.com/paper/2407.11102/) (2024)

## Abstract (arXiv)

Learning time-series representations for discriminative tasks, such as classification and regression, has been a long-standing challenge in the healthcare domain. Current pre-training methods are limited in either unidirectional next-token prediction or randomly masked token prediction. We propose a novel architecture called Bidirectional Timely Generative Pre-trained Transformer (BiTimelyGPT), which pre-trains on biosignals and longitudinal clinical records by both next-token and previous-token prediction in alternating transformer layers. This pre-training task preserves original distribution and data shapes of the time-series. Additionally, the full-rank forward and backward attention matrices exhibit more expressive representation capabilities. Using biosignals and longitudinal clinical records, BiTimelyGPT demonstrates superior performance in predicting neurological functionality, disease diagnosis, and physiological signs. By visualizing the attention heatmap, we observe that the pre-trained BiTimelyGPT can identify discriminative segments from biosignal time-series sequences, even more so after fine-tuning on the task.