Equivariant Transformer (ET) layers are image-to-image mappings that incorporate prior knowledge on invariances with respect to continuous transformations groups (ICML 2019). Paper: https://arxiv.org/abs/1901.11399

Code repository for the paper "Attentive Group Equivariant Convolutional Neural Networks" published at ICML 2020. https://arxiv.org/abs/2002.03830

Repo for "On Learning Symmetric Locomotion"

Implementation of Lie Transformer, Equivariant Self-Attention, in Pytorch

Tensorflow 2 / tf.keras port of keras-gcnn.

Code for SIGGRAPH paper CNNs on Surfaces using Rotation-Equivariant Features

[ICLR 2021] Group Equivariant Generative Adversarial Networks.

Tensorflow 2 port of Group Equivariant Convolutional Neural Networks

Official implementation of the ICML 2020 paper "PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions".

Implementation of Geometric Vector Perceptron, a simple circuit for 3d rotation equivariance for learning over large biomolecules, in Pytorch. Idea proposed and accepted at ICLR 2021

Original code for "Exploiting Learned Symmetries in Group Equivariant Convolutions"

A short and easy PyTorch implementation of E(n) Equivariant Graph Neural Networks

Authors' implementation of the paper "Equivariant Networks for Pixelized Spheres" published at ICML 2021.

Code repository of the paper "Exploiting Redundancy: Separable Group Convolutional Networks on Lie Groups" https://proceedings.mlr.press/v162/knigge22a.html

Experiments with Group Equivariant Convolutional Networks

[NeurIPS'21] Higher-order Transformers for sets, graphs, and hypergraphs, in PyTorch

Image to Icosahedral Projection for SO(3) Object Reasoning from Single-View Images

Understanding and Extending Subgraph GNNs by Rethinking their Symmetries (NeurIPS 2022 Oral)

Official source code for "Roto-translated Local Coordinate Frames For Interacting Dynamical Systems". In NeurIPS 2021.

[ECCV'22] Equivariant Hypergraph Neural Networks, in PyTorch