# Temporal Label Smoothing for Early Event Prediction

arXiv: https://arxiv.org/abs/2208.13764 · HTML: https://mlsanity.com/paper/2208.13764/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 55 references that are in the map.
- First posted on arXiv 29 Aug 2022.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Multitask learning and benchmarking with clinical time series data](https://mlsanity.com/paper/1703.07771/) (2017)
- [cuDNN: Efficient Primitives for Deep Learning](https://mlsanity.com/paper/1410.0759/) (2014)
- [Multi-Time Attention Networks for Irregularly Sampled Time Series](https://mlsanity.com/paper/2101.10318/) (2021)
- [Does label smoothing mitigate label noise?](https://mlsanity.com/paper/2003.02819/) (2020)
- [Delving into Deep Imbalanced Regression](https://mlsanity.com/paper/2102.09554/) (2021)
- [Set Functions for Time Series](https://mlsanity.com/paper/1909.12064/) (2019)
- [PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions](https://mlsanity.com/paper/2204.12511/) (2022)
- [Deep Recurrent Survival Analysis](https://mlsanity.com/paper/1809.02403/) (2018)
- [Learning to Detect Sepsis with a Multitask Gaussian Process RNN Classifier](https://mlsanity.com/paper/1706.04152/) (2017)
- [Generalized Entropy Regularization or: There's Nothing Special about Label Smoothing](https://mlsanity.com/paper/2005.00820/) (2020)
- [HiRID-ICU-Benchmark -- A Comprehensive Machine Learning Benchmark on High-resolution ICU Data](https://mlsanity.com/paper/2111.08536/) (2021)
- [Regularization via Structural Label Smoothing](https://mlsanity.com/paper/2001.01900/) (2020)
- [Early detection of sepsis utilizing deep learning on electronic health record event sequences](https://mlsanity.com/paper/1906.02956/) (2019)
- [Survival stacking: casting survival analysis as a classification problem](https://mlsanity.com/paper/2107.13480/) (2021)
- [Evaluating Progress on Machine Learning for Longitudinal Electronic Healthcare Data](https://mlsanity.com/paper/2010.01149/) (2020)
- [Disability prediction in multiple sclerosis using performance outcome measures and demographic data](https://mlsanity.com/paper/2204.03969/) (2022)

## Built on by (most cited first, 12 of 12)

- [Dynamic Survival Analysis for Early Event Prediction](https://mlsanity.com/paper/2403.12818/) (2024)
- [Incremental Sequence Classification with Temporal Consistency](https://mlsanity.com/paper/2505.16548/) (2025)
- [RiskProp: Collision-Anchored Self-Supervised Risk Propagation for Early Accident Anticipation](https://mlsanity.com/paper/2603.27165/) (2026)
- [Data-Driven Discovery of Feature Groups in Clinical Time Series](https://mlsanity.com/paper/2511.08260/) (2025)
- [Towards Dynamic Feature Acquisition on Medical Time Series by Maximizing Conditional Mutual Information](https://mlsanity.com/paper/2407.13429/) (2024)
- [Stable Prediction of Adverse Events in Medical Time-Series Data](https://mlsanity.com/paper/2510.14286/) (2025)
- [Early Warning of Intraoperative Adverse Events via Transformer-Driven Multi-Label Learning](https://mlsanity.com/paper/2603.05212/) (2026)
- [MATA-Former & SIICU: Semantic Aware Temporal Alignment for High-Fidelity ICU Risk Prediction](https://mlsanity.com/paper/2604.01727/) (2026)
- [ChunQiuTR: Time-Keyed Temporal Retrieval in Classical Chinese Annals](https://mlsanity.com/paper/2604.06997/) (2026)
- [Event-Based Early Warning of Vineyard Disease Risk from Environmental Time Series](https://mlsanity.com/paper/2605.04548/) (2026)
- [Weighted Score-Oriented Losses for Temporally Localized Event Prediction](https://mlsanity.com/paper/2606.23145/) (2026)
- [Horizon-Aware Early Event Prediction for Tokamak Disruption Alarms](https://mlsanity.com/paper/2609.24443/) (2026)

## Abstract (arXiv)

Models that can predict the occurrence of events ahead of time with low false-alarm rates are critical to the acceptance of decision support systems in the medical community. This challenging task is typically treated as a simple binary classification, ignoring temporal dependencies between samples, whereas we propose to exploit this structure. We first introduce a common theoretical framework unifying dynamic survival analysis and early event prediction. Following an analysis of objectives from both fields, we propose Temporal Label Smoothing (TLS), a simpler, yet best-performing method that preserves prediction monotonicity over time. By focusing the objective on areas with a stronger predictive signal, TLS improves performance over all baselines on two large-scale benchmark tasks. Gains are particularly notable along clinically relevant measures, such as event recall at low false-alarm rates. TLS reduces the number of missed events by up to a factor of two over previously used approaches in early event prediction.