教你怎么让图神经网络理解分子旋转对称性。
A Complete Guide to Spherical Equivariant Graph Transformers
- 用球张量和SO(3)群表示法构建旋转不变的模型
- 实现蛋白质等三维结构的物理合理预测
- 适合做分子性质预测与结构建模的研究者
球面等变图神经网络（EGNNs）为学习三维分子和生物分子系统提供了一个严谨框架，其预测需遵循物理固有的旋转对称性。这类模型通过将节点和边特征表示为在旋转群SO(3)的不可约表示下变换的球张量，扩展了传统消息传递GNN和Transformer，确保输入旋转时输出以物理上合理的方式变化。本指南系统构建了球面等变建模的完整直观基础——从群表示、球谐函数，到张量积、Clebsch-Gordan分解，以及SO(3)等变核的构造。基于此基础，我们构建了张量场网络（Tensor Field Network）和SE(3)-Transformer架构，并解释它们如何在几何图上执行等变消息传递与注意力机制。通过清晰的数学推导和带注释的代码片段，本指南为希望理解或实现球面EGNN应用于化学、分子性质预测、蛋白质结构建模及生成建模的研究人员和学习者提供了自包含的入门资料。
原文摘要 · Abstract (English)
Spherical equivariant graph neural networks (EGNNs) provide a principled framework for learning on three-dimensional molecular and biomolecular systems, where predictions must respect the rotational symmetries inherent in physics. These models extend traditional message-passing GNNs and Transformers by representing node and edge features as spherical tensors that transform under irreducible representations of the rotation group SO(3), ensuring that predictions change in physically meaningful ways under rotations of the input. This guide develops a complete, intuitive foundation for spherical equivariant modeling - from group representations and spherical harmonics, to tensor products, Clebsch-Gordan decomposition, and the construction of SO(3)-equivariant kernels. Building on this foundation, we construct the Tensor Field Network and SE(3)-Transformer architectures and explain how they perform equivariant message-passing and attention on geometric graphs. Through clear mathematical derivations and annotated code excerpts, this guide serves as a self-contained introduction for researchers and learners seeking to understand or implement spherical EGNNs for applications in chemistry, molecular property prediction, protein structure modeling, and generative modeling.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。