Adaptive Sampling for Continuous Group Equivariant Neural Networks

Berfin Inal, Gabriele Cesa

Track: Proceedings

Keywords: adaptive sampling, steerable networks, equivariant networks, computational efficiency

TL;DR: We present an adaptive sampling approach for equivariant networks that reduces the need for extensive sampling, and thereby lowers the computational costs.

Abstract:

Steerable networks, which process data with intrinsic symmetries, often use Fourier-based non-linearities that require sampling from the entire group, leading to a need for discretization in continuous groups. As the number of samples increases, both performance and equivariance improve, yet this also leads to higher computational costs. To address this, we introduce an adaptive sampling approach that dynamically adjusts the sampling process to the symmetries in the data, reducing the number of required group samples and lowering the computational demands. We explore various implementations and their effects on model performance, equivariance, and computational efficiency. Our findings demonstrate improved model performance, and a marginal increase in memory
efficiency.

Submission Number: 94