# Differential Learning for Robust Prediction of Thermal Stability with Application to Energetic Materials

arXiv: https://arxiv.org/abs/2608.23874 · HTML: https://mlsanity.com/paper/2608.23874/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 73 references that are in the map.
- First posted on arXiv 24 Aug 2026.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Tune: A Research Platform for Distributed Model Selection and Training](https://mlsanity.com/paper/1807.05118/) (2018)
- [A System for Massively Parallel Hyperparameter Tuning](https://mlsanity.com/paper/1810.05934/) (2018)
- [Robustness of classifiers: from adversarial to random noise](https://mlsanity.com/paper/1608.08967/) (2016)
- [Graph-based Molecular Representation Learning](https://mlsanity.com/paper/2207.04869/) (2022)
- [MolScribe: Robust Molecular Structure Recognition with Image-To-Graph Generation](https://mlsanity.com/paper/2205.14311/) (2022)
- [Graph Neural Networks for Molecules](https://mlsanity.com/paper/2209.05582/) (2022)
- [MolNexTR: A Generalized Deep Learning Model for Molecular Image Recognition](https://mlsanity.com/paper/2403.03691/) (2024)
- [Twin Neural Network Regression](https://mlsanity.com/paper/2012.14873/) (2020)
- [Data Fusion of Deep Learned Molecular Embeddings for Property Prediction](https://mlsanity.com/paper/2504.07297/) (2025)
- [Active Learning for Generalizable Detonation Performance Prediction of Energetic Materials](https://mlsanity.com/paper/2604.08744/) (2026)

## Abstract (arXiv)

Predicting thermal stability during handling and storage is essential for the design of safe and reliable energetic materials. However, experimental measurements vary significantly across laboratories due to differences in protocols and analysis methods, making it difficult to train reliable predictive models. We address this challenge through differential learning. Rather than predicting absolute decomposition temperatures, we instead train message passing neural networks to predict relative differences between pairs of molecules. This approach reduces sensitivity to systematic experimental errors and achieves >85% accuracy in ranking compounds by thermal stability, outperforming conventional regression methods on the same heterogeneous dataset. To understand what drives these predictions, we compare neural network models with interpretable alternatives built from descriptors derived from ab initio calculations and cheminformatics software. This analysis identifies bond dissociation enthalpy as a key determinant of thermal stability rankings, providing further insight into the complex chemistry of thermal decomposition. The differential learning framework generalizes across model architectures, from graph neural networks to classical descriptor-based approaches. Our results demonstrate that learning relative properties rather than absolute values offers a practical solution for modeling noisy experimental data, with direct applications in materials design where thermal stability predictions inform safety protocols.