paper-with-me

Papers

A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups

2021-04-19 · Marc Finzi, Max Welling, Andrew Gordon Wilson

Symmetries and equivariance are fundamental to the generalization of neural networks on domains such as images, graphs, and point clouds. Existing work has primarily focused on a small number of groups, such as the translation, rotation, and permutation groups. In this work we provide a completely general algorithm for solving for the equivariant layers of matrix groups. In addition to recovering solutions from other works as special cases, we construct multilayer perceptrons equivariant to multiple groups that have never been tackled before, including $\mathrm{O}(1,3)$, $\mathrm{O}(5)$, $\mathrm{Sp}(n)$, and the Rubik's cube group. Our approach outperforms non-equivariant baselines, with applications to particle physics and dynamical systems. We release our software library to enable researchers to construct equivariant layers for arbitrary matrix groups.

📄 PDF Abstract BibTeX arXiv:2104.09459

Code (4)

mfinzi/equivariant-MLP 공식 구현 jax
researchworking/scalaremlp jax
weichiyao/scalaremlp jax
zichunhao/lgn-autoencoder pytorch

Tasks

Rubik's CubeTranslation

Similar Papers 제목 키워드 기반

Universal Equivariant Multilayer Perceptrons

2020-02-07 · ICML 2020 1 · Siamak Ravanbakhsh

Group invariant and equivariant Multilayer Perceptrons (MLP), also known as Equivariant Networks, have achieved remarkable success in learning on a variety of data structures, such as sequences, images, sets, and graphs.…

Symmetry Breaking and Equivariant Neural Networks

2023-12-14 · Sékou-Oumar Kaba, Siamak Ravanbakhsh

Using symmetry as an inductive bias in deep learning has been proven to be a principled approach for sample-efficient model design. However, the relationship between symmetry and the imperative for equivariance in neural…

Combinatorial OptimizationGraph Representation LearningInductive BiasRepresentation Learning

Autoencoders, Kernels, and Multilayer Perceptrons for Electron Micrograph Restoration and Compression

2018-08-29 · Jeffrey M. Ede

We present 14 autoencoders, 15 kernels and 14 multilayer perceptrons for electron micrograph restoration and compression. These have been trained for transmission electron microscopy (TEM), scanning transmission electron…

Denoising

LEAPS: A discrete neural sampler via locally equivariant networks

2025-02-15 · Peter Holderrieth, Michael S. Albergo, Tommi Jaakkola

We propose LEAPS, an algorithm to sample from discrete distributions known up to normalization by learning a rate matrix of a continuous-time Markov chain (CTMC). LEAPS can be seen as a continuous-time formulation of ann…

Universal Collection of Euclidean Invariants between Pairs of Position-Orientations

2025-04-04 · Gijs Bellaard, Bart M. N. Smets, Remco Duits

Euclidean E(3) equivariant neural networks that employ scalar fields on position-orientation space M(3) have been effectively applied to tasks such as predicting molecular dynamics and properties. To perform equivariant …

Position