mlsanityData to 7 Oct 2026

Informing Geometric Deep Learning with Electronic Interactions to Accelerate Quantum Chemistry

arXiv 2105.14655 ↗First posted 31 May 2021cs.LG physics.chem-phcited by 27

Not on the map. Why?

Abstract (arXiv)

Predicting electronic energies, densities, and related chemical properties can facilitate the discovery of novel catalysts, medicines, and battery materials. By developing a physics-inspired equivariant neural network, we introduce a method to learn molecular representations based on the electronic interactions among atomic orbitals. Our method, OrbNet-Equi, leverages efficient tight-binding simulations and learned mappings to recover high fidelity quantum chemical properties. OrbNet-Equi models a wide spectrum of target properties with an accuracy consistently better than standard machine learning methods and a speed orders of magnitude greater than density functional theory. Despite only using training samples collected from readily available small-molecule libraries, OrbNet-Equi outperforms traditional methods on comprehensive downstream benchmarks that encompass diverse main-group chemical processes. Our method also describes interactions in challenging charge-transfer complexes and open-shell systems. We anticipate that the strategy presented here will help to expand opportunities for studies in chemistry and materials science, where the acquisition of experimental or reference training data is costly.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 27 of its 121 references that are in the map. First posted on arXiv 31 May 2021.

Builds on

27 of 121 references.

References · 27

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  3. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  4. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  5. 2015Fast R-CNNcited by 2,930
  6. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,194
  7. 2016Group Equivariant Convolutional Networkscited by 1,154
  8. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,131
  9. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 735
  10. 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 701
  11. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 602
  12. 2017SchNet: A continuous-filter convolutional neural network for modeling quantum interactionscited by 569
15 more
  1. 2020Directional Message Passing for Molecular Graphscited by 556
  2. 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 438
  3. 20183D Steerable CNNs: Learning Rotationally Equivariant Features in Volumetric Datacited by 348
  4. 2019Cormorant: Covariant Molecular Neural Networkscited by 262
  5. 2020Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Moleculescited by 254
  6. 2017Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanicscited by 213
  7. 2018Clebsch-Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Networkcited by 168
  8. 2020OrbNet: Deep Learning for Quantum Chemistry Using Symmetry-Adapted Atomic-Orbital Featurescited by 63
  9. 2020A Wigner-Eckart Theorem for Group Equivariant Convolution Kernelscited by 46
  10. 2020Kohn-Sham equations as regularizer: building prior knowledge into machine-learned physicscited by 36
  11. 2020Automated Synthetic-to-Real Generalizationcited by 35
  12. 2020Predicting molecular dipole moments by combining atomic partial charges and atomic dipolescited by 18
  13. 2020DeepDFT: Neural Message Passing Network for Accurate Charge Density Predictioncited by 12
  14. 2019A Universal Density Matrix Functional from Molecular Orbital-Based Machine Learning: Transferability across Organic Moleculescited by 9
  15. 2020Multi-task learning for electronic structure to predict and explore molecular potential energy surfacescited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 5; 2023: 5; 2024: 7; 2025: 5; 2026: 4.

27 papers.

Sort:

By area:

  1. 2023Fast, Expressive SE(n) Equivariant Networks through Weight-Sharing in Position-Orientation Spacecited by 40
  2. 2024Complete and Efficient Graph Transformers for Crystal Material Property Predictioncited by 34
  3. 2021Equivariant graph neural networks for fast electron density estimation of molecules, liquids, and solidscited by 24
  4. 2022Fast Uncertainty Estimates in Deep Learning Interatomic Potentialscited by 22
  5. 2022Graph Neural Networks for Moleculescited by 21
  6. 2023CHGNet: Pretrained universal neural network potential for charge-informed atomistic modelingcited by 13
  7. 2023Higher-Order Equivariant Neural Networks for Charge Density Prediction in Materialscited by 12
  8. 2025ELECTRA: A Cartesian Network for 3D Charge Density Prediction with Floating Orbitalscited by 9
  9. 2024Image Super-resolution Inspired Electron Density Predictioncited by 8
  10. 2024A Recipe for Charge Density Predictioncited by 8
  11. 2024FeNNol: an Efficient and Flexible Library for Building Force-field-enhanced Neural Network Potentialscited by 6
  12. 2024Infusing Self-Consistency into Density Functional Theory Hamiltonian Prediction via Deep Equilibrium Modelscited by 6
15 more
  1. 2022A smooth basis for atomistic machine learningcited by 4
  2. 2025Equivariant Machine Learning Interatomic Potentials with Global Charge Redistributioncited by 4
  3. 2025OrbitAll: A Unified Quantum Mechanical Representation Deep Learning Framework for All Molecular Systemscited by 4
  4. 2023High Accuracy Uncertainty-Aware Interatomic Force Modeling with Equivariant Bayesian Neural Networkscited by 2
  5. 2022Molecular Dipole Moment Learning via Rotationally Equivariant Gaussian Process Regression with Derivatives in Molecular-orbital-based Machine Learningcited by 1
  6. 2022Molecular-orbital-based Machine Learning for Open-shell and Multi-reference Systems with Kernel Addition Gaussian Process Regressioncited by 1
  7. 2023Investigating the Behavior of Diffusion Models for Accelerating Electronic Structure Calculationscited by 1
  8. 2024NeuralSCF: Neural network self-consistent fields for density functional theorycited by 1
  9. 2024FreeCG: Free the Design Space of Clebsch-Gordan Transform for Machine Learning Force Fieldscited by 1
  10. 2026Global Plane Waves From Local Gaussians: Periodic Charge Densities in a Blinkcited by 1
  11. 2026MARA: Continuous SE(3)-Equivariant Attention for Molecular Force Fieldscited by 1
  12. 2025On-the-Fly Fine-Tuning of Foundational Neural Network Potentials: A Bayesian Neural Network Approachcited by 0
  13. 2025Predictive Free Energy Simulations Through Hierarchical Distillation of Quantum Hamiltonianscited by 0
  14. 2026GDEGAN: Gaussian Dynamic Equivariant Graph Attention Network for Ligand Binding Site Predictioncited by 0
  15. 2026Closing the Prior-Posterior Loop: Self-Reflective Molecular Design with Analysis-Driven LLM Iterationcited by 0