Implicit Convolutional Kernels for Steerable CNNs

Maksim Zhdanov, Nico Hoffmann, Gabriele Cesa

Keywords: equivariance; group convolutions; implicit kernels; physical simulations

TL;DR: The paper proposed parameterizing steerable kernels with group equivariant MLPs, providing a flexible approach that can generalize to different symmetry transformations and demonstrates its effectiveness in various tasks.

Abstract: Steerable convolutional neural networks (CNNs) provide a general framework for building neural networks equivariant to translations and transformations of an origin-preserving group $G$, such as reflections and rotations. They rely on standard convolutions with $G$-steerable kernels obtained by analytically solving the group-specific equivariance constraint imposed onto the kernel space. As the solution is tailored to a particular group $G$, implementing a kernel basis does not generalize to other symmetry transformations, complicating the development of general group equivariant models. We propose using implicit neural representation via multi-layer perceptrons (MLPs) to parameterize $G$-steerable kernels. The resulting framework offers a simple and flexible way to implement Steerable CNNs and generalizes to any group $G$ for which a $G$-equivariant MLP can be built. We prove the effectiveness of our method on multiple tasks, including N-body simulations, point cloud classification and molecular property prediction.

Submission Number: 7886