# Back2Future: Leveraging Backfill Dynamics for Improving Real-time Predictions in Future

arXiv: https://arxiv.org/abs/2106.04420 · HTML: https://mlsanity.com/paper/2106.04420/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 72 references that are in the map.
- First posted on arXiv 8 Jun 2021.

## Builds on (most cited first, 16 of 16)

- [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)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [Sequential Neural Processes](https://mlsanity.com/paper/1906.10264/) (2019)
- [Interpretable Sequence Learning for COVID-19 Forecasting](https://mlsanity.com/paper/2008.00646/) (2020)
- [Inter-Series Attention Model for COVID-19 Forecasting](https://mlsanity.com/paper/2010.13006/) (2020)
- [Accurate estimation of influenza epidemics using Google search data via ARGO](https://mlsanity.com/paper/1505.00864/) (2015)
- [Robustifying Sequential Neural Processes](https://mlsanity.com/paper/2006.15987/) (2020)
- [Steering a Historical Disease Forecasting Model Under a Pandemic: Case of Flu and COVID-19](https://mlsanity.com/paper/2009.11407/) (2020)
- [Curating a COVID-19 data repository and forecasting county-level death counts in the United States](https://mlsanity.com/paper/2005.07882/) (2020)
- [HoloScope: Topology-and-Spike Aware Fraud Detection](https://mlsanity.com/paper/1705.02505/) (2017)
- [Multivariate Hierarchical Frameworks for Modelling Delayed Reporting in Count Data](https://mlsanity.com/paper/1904.03397/) (2019)
- [Gaussian Process Nowcasting: Application to COVID-19 Mortality Reporting](https://mlsanity.com/paper/2102.11249/) (2021)
- [Transfer Graph Neural Networks for Pandemic Forecasting](https://mlsanity.com/paper/2009.08388/) (2020)

## Built on by (most cited first, 7 of 7)

- [EINNs: Epidemiologically-informed Neural Networks](https://mlsanity.com/paper/2202.10446/) (2022)
- [Differentiable Agent-based Epidemiology](https://mlsanity.com/paper/2207.09714/) (2022)
- [CAMul: Calibrated and Accurate Multi-view Time-Series Forecasting](https://mlsanity.com/paper/2109.07438/) (2021)
- [Data-Centric Epidemic Forecasting: A Survey](https://mlsanity.com/paper/2207.09370/) (2022)
- [Large Scale Hierarchical Industrial Demand Time-Series Forecasting incorporating Sparsity](https://mlsanity.com/paper/2407.02657/) (2024)
- [Improving Epidemic Analyses with Privacy-Preserving Integration of Sensitive Data](https://mlsanity.com/paper/2506.22342/) (2025)
- [Are LLMs Ready for Neural-integrated Mechanistic Modeling? A Benchmark and Agentic Framework](https://mlsanity.com/paper/2602.18008/) (2026)

## Abstract (arXiv)

In real-time forecasting in public health, data collection is a non-trivial and demanding task. Often after initially released, it undergoes several revisions later (maybe due to human or technical constraints) - as a result, it may take weeks until the data reaches to a stable value. This so-called 'backfill' phenomenon and its effect on model performance has been barely studied in the prior literature. In this paper, we introduce the multi-variate backfill problem using COVID-19 as the motivating example. We construct a detailed dataset composed of relevant signals over the past year of the pandemic. We then systematically characterize several patterns in backfill dynamics and leverage our observations for formulating a novel problem and neural framework Back2Future that aims to refines a given model's predictions in real-time. Our extensive experiments demonstrate that our method refines the performance of top models for COVID-19 forecasting, in contrast to non-trivial baselines, yielding 18% improvement over baselines, enabling us obtain a new SOTA performance. In addition, we show that our model improves model evaluation too; hence policy-makers can better understand the true accuracy of forecasting models in real-time.