Tensor Frames -- How To Make Any Message Passing Network Equivariant
In many applications of geometric deep learning, the choice of global coordinate frame is arbitrary, and predictions should be independent of the reference frame. In other words, the network should be equivariant with respect to rotations and reflections of the input, i.e., the transformations of O(d). We present a novel framework for building equivariant message passing architectures and modifying existing non-equivariant architectures to be equivariant. Our approach is based on local coordinate frames, between which geometric information is communicated consistently by including tensorial objects in the messages. Our framework can be applied to message passing on geometric data in arbitrary dimensional Euclidean space. While many other approaches for equivariant message passing require specialized building blocks, such as non-standard normalization layers or non-linearities, our approach can be adapted straightforwardly to any existing architecture without such modifications. We explicitly demonstrate the benefit of O(3)-equivariance for a popular point cloud architecture and produce state-of-the-art results on normal vector regression on point clouds.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Direct Molecular Polarizability Prediction with SO(3) Equivariant Local Frame GNNs
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 de…
Molecular Property PredictionGraph Neural NetworkLorentz Local Canonicalization: How to Make Any Network Lorentz-Equivariant
Lorentz-equivariant neural networks are becoming the leading architectures for high-energy physics. Current implementations rely on specialized layers, limiting architectural choices. We introduce Lorentz Local Canonical…
Data AugmentationEquivariance by Local Canonicalization: A Matter of Representation
Equivariant neural networks offer strong inductive biases for learning from molecular and geometric data but often rely on specialized, computationally expensive tensor operations. We present a framework to transfers exi…
Learning Local Equivariant Representations for Large-Scale Atomistic Dynamics
A simultaneously accurate and computationally efficient parametrization of the energy and atomic forces of molecules and materials is a long-standing goal in the natural sciences. In pursuit of this goal, neural message …
Atomic ForcesP-tensors: a General Formalism for Constructing Higher Order Message Passing Networks
Several recent papers have recently shown that higher order graph neural networks can achieve better accuracy than their standard message passing counterparts, especially on highly structured graphs such as molecules. Th…