mlsanityData to 7 Oct 2026

Equivariant Masked Position Prediction for Efficient Molecular Representation

arXiv 2502.08209 ↗First posted 12 Feb 2025cs.LG cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Graph neural networks (GNNs) have shown considerable promise in computational chemistry. However, the limited availability of molecular data raises concerns regarding GNNs' ability to effectively capture the fundamental principles of physics and chemistry, which constrains their generalization capabilities. To address this challenge, we introduce a novel self-supervised approach termed Equivariant Masked Position Prediction (EMPP), grounded in intramolecular potential and force theory. Unlike conventional attribute masking techniques, EMPP formulates a nuanced position prediction task that is more well-defined and enhances the learning of quantum mechanical features. EMPP also bypasses the approximation of the Gaussian mixture distribution commonly used in denoising methods, allowing for more accurate acquisition of physical properties. Experimental results indicate that EMPP significantly enhances performance of advanced molecular architectures, surpassing state-of-the-art self-supervised approaches. Our code is released in https://github.com/ajy112/EMPP

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 29 of its 41 references that are in the map. First posted on arXiv 12 Feb 2025.

Builds on

29 of 41 references.

References · 29

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2019Strategies for Pre-training Graph Neural Networkscited by 964
  3. 2018Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point cloudscited by 735
  4. 2018Spherical CNNscited by 452
  5. 2022GraphMAE: Self-Supervised Masked Graph Autoencoderscited by 443
  6. 2021Equivariant message passing for the prediction of tensorial properties and molecular spectracited by 438
  7. 2019Hyperbolic Graph Convolutional Neural Networkscited by 400
  8. 2022Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphscited by 258
  9. 2020Fast and Uncertainty-Aware Directional Message Passing for Non-Equilibrium Moleculescited by 254
  10. 2020The Open Catalyst 2020 (OC20) Dataset and Community Challengescited by 246
  11. 2020GEOM: Energy-annotated molecular conformations for property prediction and molecular generationcited by 238
  12. 2021Geometric and Physical Quantities Improve E(3) Equivariant Message Passingcited by 225
17 more
  1. 2023EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representationscited by 201
  2. 2022TorchMD-NET: Equivariant Transformers for Neural Network based Molecular Potentialscited by 179
  3. 2018Clebsch-Gordan Nets: a Fully Fourier Space Spherical Convolutional Neural Networkcited by 168
  4. 2021Motif-based Graph Self-Supervised Learning for Molecular Property Predictioncited by 159
  5. 2022Pre-training via Denoising for Molecular Property Predictioncited by 124
  6. 2023Reducing SO(3) Convolutions to SO(2) for Efficient Equivariant GNNscited by 113
  7. 2022One Transformer Can Understand Both 2D & 3D Molecular Datacited by 77
  8. 2022Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matchingcited by 67
  9. 2020TorchMD: A deep learning framework for molecular simulationscited by 55
  10. 2022Spherical Channels for Modeling Atomic Interactionscited by 47
  11. 2022Energy-Motivated Equivariant Pretraining for 3D Molecular Graphscited by 37
  12. 2023Fractional Denoising for 3D Molecular Pre-trainingcited by 33
  13. 2023Highly Accurate Quantum Chemical Property Prediction with Uni-Mol+cited by 22
  14. 2022Graph Self-supervised Learning with Accurate Discrepancy Learningcited by 21
  15. 2023Symphony: Symmetry-Equivariant Point-Centered Spherical Harmonics for 3D Molecule Generationcited by 17
  16. 2023Motif-aware Attribute Masking for Molecular Graph Pre-trainingcited by 16
  17. 2023Artificial Intelligence for Drug Discovery: Are We There Yet?cited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 3.

4 papers.

  1. 2025Self-Supervised Learning on Molecular Graphs: A Systematic Investigation of Masking Designcited by 1
  2. 2026PCEvo: Path-Consistent Molecular Representation via Virtual Evolutionarycited by 1
  3. 2026Suiren-1.0 Technical Report: A Family of Molecular Foundation Modelscited by 1
  4. 2026When Molecular Similarity Works: Property Cliffs Reveal Hidden Errorscited by 0