Direct Molecular Polarizability Prediction with SO(3) Equivariant Local Frame GNNs

• URL: http://arxiv.org/abs/2511.07087v1
• Date: Mon, 10 Nov 2025 13:23:20 GMT
• Title: Direct Molecular Polarizability Prediction with SO(3) Equivariant Local Frame GNNs
• Authors: Jean Philip Filling, Felix Post, Michael Wand, Denis Andrienko,
• Abstract summary: We introduce a novel equivariant graph neural network architecture designed to predict the tensorial response properties of molecules.<n>Our GNN effectively captures geometric information by integrating scalar, vector, and tensor channels within a local message-passing framework.<n>To assess the accuracy of our model, we apply it to predict the polarizabilities of molecules in the QM7-X dataset and show that tensorial message passing outperforms scalar message passing models.
• Score: 2.9853030364785003
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce a novel equivariant graph neural network (GNN) architecture designed to predict the tensorial response properties of molecules. Unlike traditional frameworks that focus on regressing scalar quantities and derive tensorial properties from their derivatives, our approach maintains $SO(3)$-equivariance through the use of local coordinate frames. Our GNN effectively captures geometric information by integrating scalar, vector, and tensor channels within a local message-passing framework. To assess the accuracy of our model, we apply it to predict the polarizabilities of molecules in the QM7-X dataset and show that tensorial message passing outperforms scalar message passing models. This work marks an advancement towards developing structured, geometry-aware neural models for molecular property prediction.

Related papers

• Protein Graph Neural Networks for Heterogeneous Cryo-EM Reconstruction [5.264562311559749]
  We present a geometry-aware method for heterogeneous single-particle cryogenic electron microscopy (cryo-EM) reconstruction.<n>We represent the backbone as a graph and use a graph neural network (GNN) autodecoder that maps per-image latent variables to 3D displacements of a template conformation.
  arXiv  Detail & Related papers  (2026-02-25T13:43:52Z)
• A Complete Guide to Spherical Equivariant Graph Transformers [0.7953056533753116]
  Spherical equivariant graph neural networks (EGNNs) provide a principled framework for learning on three-dimensional molecular and biomolecular systems.<n>This guide serves as a self-contained introduction for researchers and learners seeking to understand or implement spherical EGNNs.
  arXiv  Detail & Related papers  (2025-12-15T22:03:09Z)
• Equivariant Graph Neural Operator for Modeling 3D Dynamics [148.98826858078556]
  We propose Equivariant Graph Neural Operator (EGNO) to directly models dynamics as trajectories instead of just next-step prediction. EGNO explicitly learns the temporal evolution of 3D dynamics where we formulate the dynamics as a function over time and learn neural operators to approximate it. Comprehensive experiments in multiple domains, including particle simulations, human motion capture, and molecular dynamics, demonstrate the significantly superior performance of EGNO against existing methods.
  arXiv  Detail & Related papers  (2024-01-19T21:50:32Z)
• A quatum inspired neural network for geometric modeling [14.214656118952178]
  We introduce an innovative equivariant Matrix Product State (MPS)-based message-passing strategy. Our method effectively models complex many-body relationships, suppressing mean-field approximations. It seamlessly replaces the standard message-passing and layer-aggregation modules intrinsic to geometric GNNs.
  arXiv  Detail & Related papers  (2024-01-03T15:59:35Z)
• Tensor Decomposition Based Attention Module for Spiking Neural Networks [18.924242014716647]
  We design the textitprojected full attention (PFA) module, which demonstrates excellent results with linearly growing parameters. Our method achieves state-of-the-art performance on both static and dynamic benchmark datasets.
  arXiv  Detail & Related papers  (2023-10-23T05:25:49Z)
• Learnable Filters for Geometric Scattering Modules [64.03877398967282]
  We propose a new graph neural network (GNN) module based on relaxations of recently proposed geometric scattering transforms. Our learnable geometric scattering (LEGS) module enables adaptive tuning of the wavelets to encourage band-pass features to emerge in learned representations.
  arXiv  Detail & Related papers  (2022-08-15T22:30:07Z)
• Graph neural networks for the prediction of molecular structure-property relationships [59.11160990637615]
  Graph neural networks (GNNs) are a novel machine learning method that directly work on the molecular graph. GNNs allow to learn properties in an end-to-end fashion, thereby avoiding the need for informative descriptors. We describe the fundamentals of GNNs and demonstrate the application of GNNs via two examples for molecular property prediction.
  arXiv  Detail & Related papers  (2022-07-25T11:30:44Z)
• Equivariant vector field network for many-body system modeling [65.22203086172019]
  Equivariant Vector Field Network (EVFN) is built on a novel equivariant basis and the associated scalarization and vectorization layers. We evaluate our method on predicting trajectories of simulated Newton mechanics systems with both full and partially observed data.
  arXiv  Detail & Related papers  (2021-10-26T14:26:25Z)
• GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensembles [60.12186997181117]
  Prediction of a molecule's 3D conformer ensemble from the molecular graph holds a key role in areas of cheminformatics and drug discovery. Existing generative models have several drawbacks including lack of modeling important molecular geometry elements. We propose GeoMol, an end-to-end, non-autoregressive and SE(3)-invariant machine learning approach to generate 3D conformers.
  arXiv  Detail & Related papers  (2021-06-08T14:17:59Z)
• E(n) Equivariant Graph Neural Networks [86.75170631724548]
  This paper introduces a new model to learn graph neural networks equivariant to rotations, translations, reflections and permutations called E(n)-Equivariant Graph Neural Networks (EGNNs) In contrast with existing methods, our work does not require computationally expensive higher-order representations in intermediate layers while it still achieves competitive or better performance.
  arXiv  Detail & Related papers  (2021-02-19T10:25:33Z)
• Equivariant message passing for the prediction of tensorial properties and molecular spectra [1.7188280334580197]
  We propose the polarizable atom interaction neural network (PaiNN) and improve on common molecule benchmarks over previous networks. We apply this to the simulation of molecular spectra, achieving speedups of 4-5 orders of magnitude compared to the electronic structure reference.
  arXiv  Detail & Related papers  (2021-02-05T13:00:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.