# Formulation Graphs for Mapping Structure-Composition of Battery Electrolytes to Device Performance

arXiv: https://arxiv.org/abs/2307.03811 · HTML: https://mlsanity.com/paper/2307.03811/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 99 references that are in the map.
- First posted on arXiv 7 Jul 2023.

## Builds on (most cited first, 14 of 14)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods](https://mlsanity.com/paper/1910.09457/) (2019)
- [Convolutional Networks on Graphs for Learning Molecular Fingerprints](https://mlsanity.com/paper/1509.09292/) (2015)
- [Recent Advances in Convolutional Neural Networks](https://mlsanity.com/paper/1512.07108/) (2015)
- [Molecular Graph Convolutions: Moving Beyond Fingerprints](https://mlsanity.com/paper/1603.00856/) (2016)
- [Large-Scale Chemical Language Representations Capture Molecular Structure and Properties](https://mlsanity.com/paper/2106.09553/) (2021)
- [The Synthesizability of Molecules Proposed by Generative Models](https://mlsanity.com/paper/2002.07007/) (2020)
- [Generative chemistry: drug discovery with deep learning generative models](https://mlsanity.com/paper/2008.09000/) (2020)
- [Chemi-net: a graph convolutional network for accurate drug property prediction](https://mlsanity.com/paper/1803.06236/) (2018)
- [Consistent Online Gaussian Process Regression Without the Sample Complexity Bottleneck](https://mlsanity.com/paper/2004.11094/) (2020)
- [On the equivalence of molecular graph convolution and molecular wave function with poor basis set](https://mlsanity.com/paper/2011.07929/) (2020)
- [Size doesn't matter: predicting physico- or biochemical properties based on dozens of molecules](https://mlsanity.com/paper/2107.10882/) (2021)
- [Bayesian Multi Plate High Throughput Screening of Compounds](https://mlsanity.com/paper/1709.10041/) (2017)

## Built on by (most cited first, 6 of 6)

- [COEFF-KANs: A Paradigm to Address the Electrolyte Field with KANs](https://mlsanity.com/paper/2407.20265/) (2024)
- [Improving Performance Prediction of Electrolyte Formulations with Transformer-based Molecular Representation Model](https://mlsanity.com/paper/2406.19792/) (2024)
- [MolSets: Molecular Graph Deep Sets Learning for Mixture Property Modeling](https://mlsanity.com/paper/2312.16473/) (2023)
- [CheMixHub: Datasets and Benchmarks for Chemical Mixture Property Prediction](https://mlsanity.com/paper/2506.12231/) (2025)
- [Improving Electrolyte Performance for Target Cathode Loading Using Interpretable Data-Driven Approach](https://mlsanity.com/paper/2409.01989/) (2024)
- [Chem World: A Large-Scale Benchmark and Physics-Informed Framework for Trustworthy Chemical Property Prediction](https://mlsanity.com/paper/2607.28079/) (2026)

## Abstract (arXiv)

Advanced computational methods are being actively sought for addressing the challenges associated with discovery and development of new combinatorial material such as formulations. A widely adopted approach involves domain informed high-throughput screening of individual components that can be combined into a formulation. This manages to accelerate the discovery of new compounds for a target application but still leave the process of identifying the right 'formulation' from the shortlisted chemical space largely a laboratory experiment-driven process. We report a deep learning model, Formulation Graph Convolution Network (F-GCN), that can map structure-composition relationship of the individual components to the property of liquid formulation as whole. Multiple GCNs are assembled in parallel that featurize formulation constituents domain-intuitively on the fly. The resulting molecular descriptors are scaled based on respective constituent's molar percentage in the formulation, followed by formalizing into a combined descriptor that represents a complete formulation to an external learning architecture. The use case of proposed formulation learning model is demonstrated for battery electrolytes by training and testing it on two exemplary datasets representing electrolyte formulations vs battery performance -- one dataset is sourced from literature about Li/Cu half-cells, while the other is obtained by lab-experiments related to lithium-iodide full-cell chemistry. The model is shown to predict the performance metrics like Coulombic Efficiency (CE) and specific capacity of new electrolyte formulations with lowest reported errors. The best performing F-GCN model uses molecular descriptors derived from molecular graphs that are informed with HOMO-LUMO and electric moment properties of the molecules using a knowledge transfer technique.