Skip to yearly menu bar Skip to main content


Symphony: Symmetry-Equivariant Point-Centered Spherical Harmonics for 3D Molecule Generation

Ameya Daigavane · Song Eun Kim · Mario Geiger · Tess Smidt

Halle B #6
[ ] [ Project Page ]
Thu 9 May 7:30 a.m. PDT — 9:30 a.m. PDT

Abstract: We present Symphony, an $E(3)$ equivariant autoregressive generative model for 3D molecular geometriesthat iteratively builds a molecule from molecular fragments.Existing autoregressive models such as G-SchNet and G-SphereNet for molecules utilize rotationally invariant features to respect the 3D symmetries of molecules.In contrast, Symphony uses message-passing with higher-degree $E(3)$-equivariant features.This allows a novel representation of probability distributions via spherical harmonic signals to efficiently model the 3D geometry ofmolecules. We show that Symphony is able to accurately generate small molecules from the QM9 dataset, outperforming existingautoregressive models and approaching the performance of diffusion models. Our code is available at

Chat is not available.