Geometric Mixture Models for Electrolyte Conductivity Prediction

2025-10-17

AI Summary

Electrolyte ionic conductivity prediction faces two key challenges: the lack of high-quality benchmark datasets and inadequate modeling of geometric structures and intermolecular interactions in mixed electrolyte systems. To address these, we reconstruct and enhance the CALiSol and DiffMix datasets and propose GeoMix—the first equivariant geometric graph neural network framework tailored for electrolyte mixtures. GeoMix introduces Set-SE(3) equivariance for mixed systems, a dedicated geometric interaction network (GIN) for cross-molecular geometric message passing, and a conformation-aware molecular geometric graph representation. On standardized benchmarks, GeoMix significantly outperforms MLPs, conventional GNNs, and state-of-the-art geometric GNNs. These results underscore the critical role of explicit geometric interaction modeling in property prediction and establish a new benchmark and paradigm for electrolyte conductivity prediction.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Constraint Satisfaction and Optimization: Mixed Discrete/Continuous Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks

Abstract

Accurate prediction of ionic conductivity in electrolyte systems is crucial for advancing numerous scientific and technological applications. While significant progress has been made, current research faces two fundamental challenges: (1) the lack of high-quality standardized benchmarks, and (2) inadequate modeling of geometric structure and intermolecular interactions in mixture systems. To address these limitations, we first reorganize and enhance the CALiSol and DiffMix electrolyte datasets by incorporating geometric graph representations of molecules. We then propose GeoMix, a novel geometry-aware framework that preserves Set-SE(3) equivariance-an essential but challenging property for mixture systems. At the heart of GeoMix lies the Geometric Interaction Network (GIN), an equivariant module specifically designed for intermolecular geometric message passing. Comprehensive experiments demonstrate that GeoMix consistently outperforms diverse baselines (including MLPs, GNNs, and geometric GNNs) across both datasets, validating the importance of cross-molecular geometric interactions and equivariant message passing for accurate property prediction. This work not only establishes new benchmarks for electrolyte research but also provides a general geometric learning framework that advances modeling of mixture systems in energy materials, pharmaceutical development, and beyond.

Problem

• Predicting ionic conductivity in electrolyte systems accurately
• Addressing lack of standardized benchmarks for electrolytes
• Modeling geometric structure and intermolecular interactions in mixtures

Innovation

• Geometric graph representations enhance electrolyte datasets
• GeoMix framework preserves Set-SE(3) equivariance property
• Geometric Interaction Network enables equivariant message passing