Rotational Sampling: A Plug-and-Play Encoder for Rotation-Invariant 3D Molecular GNNs

• URL: http://arxiv.org/abs/2507.01073v1
• Date: Tue, 01 Jul 2025 08:58:12 GMT
• Title: Rotational Sampling: A Plug-and-Play Encoder for Rotation-Invariant 3D Molecular GNNs
• Abstract summary: Graph neural networks (GNNs) have achieved remarkable success in molecular property prediction.<n>Traditional graph representations struggle to effectively encode the inherent 3D spatial structures of molecules.<n>This paper proposes a novel plug-and-play 3D encoding module leveraging rotational sampling.
• Score: 5.558678875187018
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Graph neural networks (GNNs) have achieved remarkable success in molecular property prediction. However, traditional graph representations struggle to effectively encode the inherent 3D spatial structures of molecules, as molecular orientations in 3D space introduce significant variability, severely limiting model generalization and robustness. Existing approaches primarily focus on rotation-invariant and rotation-equivariant methods. Invariant methods often rely heavily on prior knowledge and lack sufficient generalizability, while equivariant methods suffer from high computational costs. To address these limitations, this paper proposes a novel plug-and-play 3D encoding module leveraging rotational sampling. By computing the expectation over the SO(3) rotational group, the method naturally achieves approximate rotational invariance. Furthermore, by introducing a carefully designed post-alignment strategy, strict invariance can be achieved without compromising performance. Experimental evaluations on the QM9 and C10 Datasets demonstrate superior predictive accuracy, robustness, and generalization performance compared to existing methods. Moreover, the proposed approach maintains low computational complexity and enhanced interpretability, providing a promising direction for efficient and effective handling of 3D molecular information in drug discovery and material design.

Related papers

• Tail-Aware Post-Training Quantization for 3D Geometry Models [58.79500829118265]
  Post-Training Quantization (PTQ) enables efficient inference without retraining.<n>PTQ fails to transfer effectively to 3D models due to intricate feature distributions and prohibitive calibration overhead.<n>We propose TAPTQ, a Tail-Aware Post-Training Quantization pipeline for 3D geometric learning.
  arXiv  Detail & Related papers  (2026-02-02T07:21:15Z)
• Quantized SO(3)-Equivariant Graph Neural Networks for Efficient Molecular Property Prediction [12.753341915660073]
  This paper addresses the problem by compressing and accelerating an SO(3)-equivariant GNN using low-bit quantization techniques.<n>Experiments on the QM9 and rMD17 molecular benchmarks demonstrate that our 8-bit models achieve accuracy on energy and force predictions comparable to full-precision baselines.<n>The proposed techniques enable the deployment of symmetry-aware GNNs in practical chemistry applications with 2.37--2.73x faster inference and 4x smaller model size.
  arXiv  Detail & Related papers  (2026-01-05T15:36:04Z)
• A Lightweight 3D Anomaly Detection Method with Rotationally Invariant Features [60.76577388438418]
  3D anomaly detection (AD) is a crucial task in computer vision, aiming to identify anomalous points or regions from point cloud data.<n>Existing methods may encounter challenges when handling point clouds with changes in orientation and position because the resulting features may vary significantly.<n>We propose a novel Rotationally Invariant Features (RIF) framework for 3D AD, which maps each point into a rotationally invariant space to maintain consistency of representation.
  arXiv  Detail & Related papers  (2025-11-17T08:16:05Z)
• Scalable Non-Equivariant 3D Molecule Generation via Rotational Alignment [24.144491389884983]
  We propose an approach that relaxes such equivariant constraints.<n>A non-equivariant diffusion model is then trained over the aligned representations.<n> Experimental results demonstrate that our approach performs significantly better than previously reported non-equivariant models.
  arXiv  Detail & Related papers  (2025-06-11T21:23:56Z)
• GaussianVAE: Adaptive Learning Dynamics of 3D Gaussians for High-Fidelity Super-Resolution [7.288410309484523]
  We present a novel approach for enhancing the resolution and geometric fidelity of 3D Gaussian Splatting (3DGS) beyond native training resolution.<n>Our work breaks this limitation through a lightweight generative model that predicts and refines additional 3D Gaussians where needed most.
  arXiv  Detail & Related papers  (2025-06-09T16:13:12Z)
• Rep3D: Re-parameterize Large 3D Kernels with Low-Rank Receptive Modeling for Medical Imaging [15.142146104837005]
  Rep3D is a 3D convolutional framework that incorporates a learnable spatial volumetric prior into large kernel training.<n>Rep3D offers an interpretable, and scalable solution for 3D medical image analysis.
  arXiv  Detail & Related papers  (2025-05-26T07:12:56Z)
• Towards Unified and Lossless Latent Space for 3D Molecular Latent Diffusion Modeling [77.26556208024633]
  3D molecule generation is crucial for drug discovery and material science.<n>Existing approaches typically maintain separate latent spaces for invariant and equivariant modalities.<n>We propose textbfUAE-3D, a multi-modal VAE that compresses 3D molecules into latent sequences from a unified latent space.
  arXiv  Detail & Related papers  (2025-03-19T08:56:13Z)
• 3D Equivariant Pose Regression via Direct Wigner-D Harmonics Prediction [50.07071392673984]
  Existing methods learn 3D rotations parametrized in the spatial domain using angles or quaternions. We propose a frequency-domain approach that directly predicts Wigner-D coefficients for 3D rotation regression. Our method achieves state-of-the-art results on benchmarks such as ModelNet10-SO(3) and PASCAL3D+.
  arXiv  Detail & Related papers  (2024-11-01T12:50:38Z)
• 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)
• Rotation-Invariant Random Features Provide a Strong Baseline for Machine Learning on 3D Point Clouds [10.166033101890227]
  We propose a simple and general-purpose method for learning rotation-invariant functions of three-dimensional point cloud data. We show through experiments that our method matches or outperforms the performance of general-purpose rotation-invariant neural networks.
  arXiv  Detail & Related papers  (2023-07-27T20:18:11Z)
• Equivariant Diffusion for Molecule Generation in 3D [74.289191525633]
  This work introduces a diffusion model for molecule computation generation in 3D that is equivariant to Euclidean transformations. Experimentally, the proposed method significantly outperforms previous 3D molecular generative methods regarding the quality of generated samples and efficiency at training time.
  arXiv  Detail & Related papers  (2022-03-31T12:52:25Z)
• 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)
• Adjoint Rigid Transform Network: Task-conditioned Alignment of 3D Shapes [86.2129580231191]
  Adjoint Rigid Transform (ART) Network is a neural module which can be integrated with a variety of 3D networks. ART learns to rotate input shapes to a learned canonical orientation, which is crucial for a lot of tasks. We will release our code and pre-trained models for further research.
  arXiv  Detail & Related papers  (2021-02-01T20:58:45Z)

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.