Pith. sign in

REVIEW 8 cited by

Equivariant message passing for the prediction of tensorial properties and molecular spectra

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2102.03150 v4 pith:57VCPVWX submitted 2021-02-05 cs.LG physics.chem-ph

classification cs.LGphysics.chem-ph
keywords equivariantmessagemolecularpassingpredictionpropertiesrepresentationsdata
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Message passing neural networks have become a method of choice for learning on graphs, in particular the prediction of chemical properties and the acceleration of molecular dynamics studies. While they readily scale to large training data sets, previous approaches have proven to be less data efficient than kernel methods. We identify limitations of invariant representations as a major reason and extend the message passing formulation to rotationally equivariant representations. On this basis, we propose the polarizable atom interaction neural network (PaiNN) and improve on common molecule benchmarks over previous networks, while reducing model size and inference time. We leverage the equivariant atomwise representations obtained by PaiNN for the prediction of tensorial properties. Finally, we apply this to the simulation of molecular spectra, achieving speedups of 4-5 orders of magnitude compared to the electronic structure reference.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 268 citations worldwide. Full citation record

  1. ED-DiT: Physics-Guided Diffusion Pretraining for Transferable Molecular Representations from Electron Density

    cs.LG 2026-08 conditional novelty 6.0 of 10

    ED-DiT pretrains a diffusion transformer on electron-density point clouds with a physical electron-number constraint, and the resulting encoder outperforms scratch models across six molecular tasks.

  2. Accelerated descriptor-free path sampling for protein-ligand binding kinetics

    physics.chem-ph 2026-07 conditional novelty 6.0 of 10

    Accelerated AIMMD, combining a descriptor-free PaiNN committor with a basin-restricted OPES bias, recovers protein–ligand unbinding rates within a small factor of experiment or unbiased-MD references, whereas standard...

  3. mCGCNN: A Dual-Stream Crystal Graph Convolutional Neural Network for the Efficient Prediction of Magnetic Properties of Crystalline Materials

    cond-mat.mtrl-sci 2026-06 unverdicted novelty 6.0 of 10

    mCGCNN augments crystal graph networks with a magnetic stream and GKA-inspired descriptors to lower MAE for total magnetic moment from 2.54 to 2.02 μB and raise R² from 0.644 to 0.776 on Materials Project DFT data.

  4. InertialAR: Autoregressive 3D Molecule Generation with Inertial Frames

    cs.LG 2025-10 conditional novelty 6.0 of 10

    An autoregressive transformer with inertial-frame tokenization and geometric rotary positional encoding reports state-of-the-art validity and stability on QM9, GEOM-Drugs, and B3LYP, plus strong functional-group-condi...

  5. FLOWR.root: A flow matching based foundation model for joint multi-purpose structure-aware 3D ligand generation and affinity prediction

    q-bio.BM 2025-10 conditional novelty 6.0 of 10

    A flow-matching model jointly generates pocket-aware 3D ligands and predicts their binding affinities, reporting state-of-the-art generation and competitive affinity accuracy with a speed advantage.

  6. Distillation of atomistic foundation models across architectures and chemical domains

    physics.comp-ph 2025-06 conditional novelty 6.0 of 10

    Distillation of atomistic foundation models via synthetic data yields 10x-100x faster student potentials with near-teacher accuracy.

  7. chemtrain-deploy: A parallel and scalable framework for machine learning potentials in million-atom MD simulations

    physics.comp-ph 2025-06 conditional novelty 6.0 of 10

    A model-agnostic JAX-to-LAMMPS framework runs machine learning potentials in million-atom multi-GPU molecular dynamics with near-ideal strong and weak scaling.

  8. Machine Learning Interatomic Potentials: library for efficient training, model development and simulation of molecular systems

    physics.chem-ph 2025-05 conditional novelty 6.0 of 10

    InstaDeep's mlip library ports MACE, NequIP, and ViSNet to JAX with a JAX-MD backend, ships SPICE2-trained organics models, reports faster MD steps than its own Torch routes, and proposes a faster gated MACE variant i...

Pith tools