Equivariant Neural Networks

Follow this topic Ask about this topic

Latest papers 146

18 papers in the last four weeks, up 38% on the four weeks before. 0.1% of all new papers.

All topics

Discretizing Group-Convolutional Neural Networks for 3D Geometry in Feature Space
May 14, 2026Daniel Franzen, Jean Philip Filling, Michael WandEquivariant Neural Networks 3D Representation Learning
Johannes Gutenberg University Mainz, Germany
Spontaneous symmetry breaking and Goldstone modes for deep information propagation
May 14, 2026Nabil Iqbal, T. Anderson Keller, Yue Song +2Symmetry Breaking Equivariant Neural Networks
Dept. of Mathematical Sciences, Durham University · Kempner Institute, Harvard University · College of AI, Tsinghua University +2
Aligning Network Equivariance with Data Symmetry: A Theoretical Framework and Adaptive Approach for Image Restoration
May 13, 2026Feiyu Tan, Qi Xie, Zongben Xu +1Equivariant Neural Networks Image Restoration
School of Mathematics and Statistics, Xi’an Jiaotong University, Xi’an, Shaanxi, China
When Does Equivariance Help? Canonical Alignment in Neural Fluid Surrogates
May 12, 2026Patryk Rygiel, Julian Suk, Kak Khee Yeung +2Neural Surrogate Modeling Equivariant Neural Networks
Department of Applied Mathematics Technical Medical Centre Cardiovascular Health Technology Centre University of Twente · Department of Computer Science Munich Center for Machine Learning Technical University of Munich · Department of Surgery Amsterdam UMC, Location University of Amsterdam Atherosclerosis & Aortic diseases Amsterdam Cardiovascular Sciences
Steerable Neural ODEs on Homogeneous Spaces
May 11, 2026Emma Andersdotter, Daniel Persson, Fredrik OhlssonEquivariant Neural Networks Geometric Representation Learning
Department of Mathematics and Mathematical Statistics Umeå University Umeå SE-901 87, Sweden · Department of Mathematical Sciences2026 Chalmers University of Technology and Gothenburg University Gothenburg SE-412 96, Sweden · Department of Mathematics and Mathematical Statistics 11 Umeå University Umeå SE-901 87, Sweden
Equivariant Reinforcement Learning for Clifford Quantum Circuit Synthesis
May 11, 2026Richie Yeung, Aleks Kissinger, Rob CornishReinforcement Learning Quantum Circuit Compilation
Department of Computer Science, University of Oxford · Quantinuum · College of Computing and Data Science, Nanyang Technological University, Singapore
Diagnosing Spectral Ceilings in Equivariant Neural Force Fields
May 8, 2026Hyunmog KimMachine Learning Interatomic Potentials Spectral Bias
Independent Researcher.
Normalization Equivariance for Arbitrary Backbones, with Application to Image Denoising
May 5, 2026Youssef Saied, François FleuretImage Corruption Robustness Neural Network Robustness
Department of Computer Science, University of Geneva, Switzerland · Meta FAIR.
Symmetry, Defects, and Diffusion in Continuous-memory Recurrent Networks
May 5, 2026Hanson Hanxuan MoEquivariant Neural Networks Recurrent Neural Networks
Augmented Equivariant Mesh Networks for Anatomical Segmentation
May 4, 2026Daniel SaragihEquivariant Neural Networks Medical Image Segmentation
Department of Pathology and Molecular Medicine Queen’s University Kingston, ON K7L 3N6, Canada
Isotropic Fourier Neural Operators
May 4, 2026Michael F. StaddonFourier Neural Operator Neural PDE Solvers
Independent Researcher
Towards Accelerated SCF Workflows with Equivariant Density-Matrix Learning and Analytic Refinement
Apr 29, 2026Zuriel Y. Yescas-Ramos, Andrés Álvarez-García, Huziel E. SaucedaQuantum Chemistry Equivariant Neural Networks
Instituto de Física, Universidad Nacional Autónoma de México, Cd. de México C.P. 04510, Mexico
Monocular Depth Estimation via Neural Network with Learnable Algebraic Group and Ring Structures
Apr 27, 2026Qianlei Wang, Kexun Chen, Shaolin Zhang +3Monocular Depth Estimation Equivariant Neural Networks
Chengdu Institute of Computer Applications, Chinese Academy of Sciences, Chengdu 610213 China. · School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu 611756 China. · School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 611756 China. +1
Quasi-Equivariant Metanetworks
Apr 26, 2026Viet-Hoang Tran, An Nguyen, Benoît Guérand +2Equivariant Neural Networks
Department of Mathematics National University of Singapore
Neuro-evolutionary stochastic architectures in gauge-covariant neural fields
Apr 22, 2026Rodrigo Carmo TerinEvolutionary Optimization Equivariant Neural Networks
King Juan Carlos University, Facuty of Experimental Sciences and Technology, Department of Applied Physics, Av. del Alcalde de M´ostoles, 28933, Madrid, Spain
Learning Affine-Equivariant Proximal Operators
Apr 16, 2026Oriel Savir, Zhenghan Fang, Jeremias SulamEquivariant Neural Networks Operator Learning
Mathematical Institute for Data Science, Johns Hopkins University, Baltimore, MD 21218, USA
Image-to-Image Translation Framework Embedded with Rotation Symmetry Priors
Apr 14, 2026Feiyu Tan, Heran Yang, Qihong Duan +3Image-to-Image Translation Unpaired Image-to-Image Translation
School of Mathematics and Statistics, Xi’an Jiaotong University, Shaanxi, P.R.China · MOE Key Lab for Intelligent Networks and Networks Security, Faculty of Electronic and Information Engineering, Xi’an Jiaotong University, Shaanxi, P.R.China
Rotation Equivariant Convolutions in Deformable Registration of Brain MRI
Apr 9, 2026Arghavan Rezvani, Kun Han, Anthony T. Wu +2Medical Image Registration Deformable Image Registration
University of California, Irvine
Pixel-Translation-Equivariant Quantum Convolutional Neural Networks via Fourier Multiplexers
Apr 7, 2026Dmitry Chirkov, Igor LobanovQuantum Convolutional Neural Networks Equivariant Neural Networks
School of Physics and Engineering, ITMO University, St. Petersburg, Russia
Efficient Equivariant Transformer for Self-Driving Agent Modeling
Apr 1, 2026Scott Xu, Dian Chen, Kelvin Wong +3Autonomous Driving Equivariant Neural Networks
Waabi · University of Toronto
The Geometry of Polynomial Group Convolutional Neural Networks
Mar 31, 2026Yacoub Hendi, Daniel Persson, Magdalena LarforsConvolutional Neural Networks Polynomial Neural Networks
Uppsala University · Chalmers University of Technology
Tunable Soft Equivariance with Guarantees
Mar 27, 2026Md Ashiqur Rahman, Lim Jun Hao, Jeremiah Jiang +2Equivariant Neural Networks
Purdue University · DSO National Laboratories
Amortized Inference for Correlated Discrete Choice Models via Equivariant Neural Networks
Mar 25, 2026Easton Huch, Michael KeaneNeural Surrogate Modeling Amortized Inference
Postdoctoral Fellow, Johns Hopkins Carey Business School · Carey Distinguished Professor, Johns Hopkins Carey Business School
ReDiffuse: Rotation Equivariant Diffusion Model for Multi-focus Image Fusion
Mar 22, 2026Bo Li, Tingting Bao, Lingling Zhang +3Multi-Source Image Fusion Diffusion Models
School of Computer Science and Technology, Xi’an Jiaotong University, Xi’an, Shaanxi, China · School of Information Engineering, Chang’an University, Xi’an, Shaanxi, China
Any-Subgroup Equivariant Networks via Symmetry Breaking
Mar 19, 2026Abhinav Goel, Derek Lim, Hannah Lawrence +2Equivariant Neural Networks Equivariant GNNs
MIT · TUM · Flatiron Institute
An SO(3)-equivariant reciprocal-space neural potential for long-range interactions
Mar 19, 2026Lingfeng Zhang, Taoyong Cui, Dongzhan Zhou +6Machine Learning Interatomic Potentials Computational Materials Science
The Chinese University of Hong Kong, Hong Kong, 999077, China. · Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong, 999077, China. · Shanghai Artificial Intelligence Laboratory, Shanghai, 200232, China. +1
Learning Coordinate-based Convolutional Kernels for Continuous SE(3) Equivariant and Efficient Point Cloud Analysis
Mar 18, 2026Jaein Kim, Hee Bin Yoo, Dong-Sig Han +1Equivariant Neural Networks Point Cloud Learning
Interdisciplinary Program in Neuroscience, Seoul National University · Département d’Informatique, École Normale Supérieure (ENS) · Department of Computing, Imperial College London +1
Accurate Shift Invariant Convolutional Neural Networks Using Gaussian-Hermite Moments
Mar 17, 2026Jaspreet Singh, Petra Bosilj, Grzegorz CielniakConvolutional Neural Networks Equivariant Neural Networks
Gauge-Equivariant Intrinsic Neural Operators for Geometry-Consistent Learning of Elliptic PDE Maps
Mar 16, 2026Pengcheng ChengPDE Operator Learning Neural Operators
School of Mathematics, Jilin University, Changchun, 130012, China
Bases of Steerable Kernels for Equivariant CNNs: From 2D Rotations to the Lorentz Group
Mar 12, 2026Alan GarbarzEquivariant Neural Networks Kernel Methods
Universidad de Buenos Aires, Facultad de Ciencias Exactas y Naturales, Departamento de F´ısica. Ciudad Universitaria, pabell´on 1, 1428, Buenos Aires, Argentina. · CONICET - Universidad de Buenos Aires, Instituto de F´ısica de Buenos Aires (IFIBA). Ciudad Universitaria, pabell´on 1, 1428, Buenos Aires, Argentina.

May 14, 2026J/K move · Enter open · S save

Discretizing Group-Convolutional Neural Networks for 3D Geometry in Feature Space

Daniel Franzen, Jean Philip Filling, Michael Wand

Johannes Gutenberg University Mainz, Germany

Equivariant Neural Networks 3D Representation Learning

Open paper AskPDF arXiv

Group-convolutional neural networks (GCNNs) are among the most important methods for introducing symmetry as an inductive bias in deep learning: In each linear layer, GCNNs sample a transformation group

G

densely and correlate data and filters in different poses (with suitable anti-aliasing for steerable GCNNs) to maintain equivariance with respect to

G

. Unfortunately, applying filters to many data items resulting from this sampling is expensive (even for translations alone, i.e., in ordinary CNNs), and costs grow exponentially with increasing degrees of freedom (such as translations and rotations in 3D), which often hinders practical applications. In this paper, we propose sampling in feature space, i.e., replacing geometrically dense samples with representative samples selected by feature similarity. This decouples geometric resolution from memory and processing costs during training and inference, providing a novel way to trade off computational effort and accuracy. Our main empirical finding is that a coarse feature-space sampling already preserves classification accuracy remarkably well, which permits precomputation based on geometric similarity, accelerating the training of equivariant 3D classifiers substantially.