Litcius/Paper detail

GoFlow: efficient transition state geometry prediction with flow matching and E(3)-equivariant neural networks

Leonard Galustian, Konstantin Mark, Johannes Karwounopoulos, Maximilian P.-P. Kovar, Esther Heid

2025Digital Discovery6 citationsDOIOpen Access PDF

Abstract

E(3)-equivariant flow matching with geometric tensor networks, achieves over a hundredfold speedup in inference while improving geometric accuracy compared to the state-of-the-art. This breakthrough increase in sampling efficiency and predictive accuracy enables the practical use of deep learning-based TS generators in high-throughput settings for larger and more complex chemical systems. Our method, GoFlow, thus represents a significant methodological advancement in machine learning-based TS generation, bringing it closer to widespread use in computational chemistry workflows.

Topics & Concepts

Computer scienceSpeedupAlgorithmArtificial neural networkInferenceSampling (signal processing)Matching (statistics)Flow (mathematics)Balanced flowArtificial intelligenceDeep learningTensor (intrinsic definition)Key (lock)Statistical physicsSynthetic dataAdaptive samplingTheoretical computer scienceState (computer science)Mathematical optimizationDeep neural networksImportance samplingComputational geometryQuantumChemical processMultiscale modelingTensor productFluid Dynamics and Turbulent FlowsComputer Graphics and Visualization Techniques
GoFlow: efficient transition state geometry prediction with flow matching and E(3)-equivariant neural networks | Litcius