# Balancing Molecular Information and Empirical Data in the Prediction of Physico-Chemical Properties

arXiv: https://arxiv.org/abs/2406.08075 · HTML: https://mlsanity.com/paper/2406.08075/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 46 references that are in the map.
- First posted on arXiv 12 Jun 2024.

## Builds on (most cited first, 10 of 10)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Variational Inference: A Review for Statisticians](https://mlsanity.com/paper/1601.00670/) (2016)
- [Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges](https://mlsanity.com/paper/2104.13478/) (2021)
- [Cyclical Learning Rates for Training Neural Networks](https://mlsanity.com/paper/1506.01186/) (2015)
- [Advances in Variational Inference](https://mlsanity.com/paper/1711.05597/) (2017)
- [Machine Learning in Thermodynamics: Prediction of Activity Coefficients by Matrix Completion](https://mlsanity.com/paper/2001.10675/) (2020)
- [Hybridizing Physical and Data-driven Prediction Methods for Physicochemical Properties](https://mlsanity.com/paper/2202.08804/) (2022)
- [Perturbative Black Box Variational Inference](https://mlsanity.com/paper/1709.07433/) (2017)

## Built on by (most cited first, 3 of 3)

- [Thermodynamics-Consistent Graph Neural Networks](https://mlsanity.com/paper/2407.18372/) (2024)
- [Prediction of Diffusion Coefficients in Mixtures with Tensor Completion](https://mlsanity.com/paper/2602.23142/) (2026)
- [Predicting Activities in Aqueous Electrolyte Solutions with Hybrid Machine Learning](https://mlsanity.com/paper/2607.19114/) (2026)

## Abstract (arXiv)

Predicting the physico-chemical properties of pure substances and mixtures is a central task in thermodynamics. Established prediction methods range from fully physics-based ab-initio calculations, which are only feasible for very simple systems, over descriptor-based methods that use some information on the molecules to be modeled together with fitted model parameters (e.g., quantitative-structure-property relationship methods or classical group contribution methods), to representation-learning methods, which may, in extreme cases, completely ignore molecular descriptors and extrapolate only from existing data on the property to be modeled (e.g., matrix completion methods). In this work, we propose a general method for combining molecular descriptors with representation learning using the so-called expectation maximization algorithm from the probabilistic machine learning literature, which uses uncertainty estimates to trade off between the two approaches. The proposed hybrid model exploits chemical structure information using graph neural networks, but it automatically detects cases where structure-based predictions are unreliable, in which case it corrects them by representation-learning based predictions that can better specialize to unusual cases. The effectiveness of the proposed method is demonstrated using the prediction of activity coefficients in binary mixtures as an example. The results are compelling, as the method significantly improves predictive accuracy over the current state of the art, showcasing its potential to advance the prediction of physico-chemical properties in general.