mlsanityData to 14 Oct 2026

Reducing the Cost of Quantum Chemical Data By Backpropagating Through Density Functional Theory

arXiv 2402.04030 ↗First posted 6 Feb 2024cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Density Functional Theory (DFT) accurately predicts the quantum chemical properties of molecules, but scales as O(Nelectrons3). Sch"utt et al. (2019) successfully approximate DFT 1000x faster with Neural Networks (NN). Arguably, the biggest problem one faces when scaling to larger molecules is the cost of DFT labels. For example, it took years to create the PCQ dataset (Nakata & Shimazaki, 2017) on which subsequent NNs are trained within a week. DFT labels molecules by minimizing energy E(· ) as a "loss function." We bypass dataset creation by directly training NNs with E(· ) as a loss function. For comparison, Sch"utt et al. (2019) spent 626 hours creating a dataset on which they trained their NN for 160h, for a total of 786h; our method achieves comparable performance within 31h.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 16 of its 41 references that are in the map. First posted on arXiv 6 Feb 2024.

Builds on

16 of 41 references.

References · 16

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2020Scaling Laws for Neural Language Modelscited by 6,586
  5. 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 708
  6. 2022MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fieldscited by 474
  7. 2020The Open Catalyst 2020 (OC20) Dataset and Community Challengescited by 246
  8. 2022One Transformer Can Understand Both 2D & 3D Molecular Datacited by 77
  9. 2019Unifying machine learning and quantum chemistry -- a deep neural network for molecular wavefunctionscited by 73
  10. 2021SE(3)-equivariant prediction of molecular wavefunctions and electronic densitiescited by 67
  11. 2023Efficient and Equivariant Graph Networks for Predicting Quantum Hamiltoniancited by 39
  12. 2023Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasetscited by 39
4 more
  1. 2020Kohn-Sham equations as regularizer: building prior knowledge into machine-learned physicscited by 36
  2. 2023QH9: A Quantum Hamiltonian Prediction Benchmark for QM9 Moleculescited by 26
  3. 2021Learning the exchange-correlation functional from nature with fully differentiable density functional theorycited by 23
  4. 2023D4FT: A Deep Learning Approach to Kohn-Sham Density Functional Theorycited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 1.

4 papers.

  1. 2024Infusing Self-Consistency into Density Functional Theory Hamiltonian Prediction via Deep Equilibrium Modelscited by 6
  2. 2025Efficient Prediction of SO(3)-Equivariant Hamiltonian Matrices via SO(2) Local Framescited by 6
  3. 2025Self-Refining Training for Amortized Density Functional Theorycited by 1
  4. 2026A Fixed-Point Neural Operator for Size- and Functional-Transferable Hamiltonian Predictioncited by 0