Symmetry Structured Convolutional Neural Networks

TL;DR

This paper introduces a symmetry-structured CNN architecture that maintains symmetry in convolutional layers, leading to improved performance and fewer parameters in sequence modeling and biological structure inference tasks.

Contribution

It develops a novel CNN design that preserves symmetry in the network's layers and provides parameterizations to maintain this structure during training.

Findings

Improved accuracy in sequential recommendation tasks.

Enhanced performance in RNA secondary structure inference.

Fewer parameters needed for effective modeling.

Abstract

We consider Convolutional Neural Networks (CNNs) with 2D structured features that are symmetric in the spatial dimensions. Such networks arise in modeling pairwise relationships for a sequential recommendation problem, as well as secondary structure inference problems of RNA and protein sequences. We develop a CNN architecture that generates and preserves the symmetry structure in the network's convolutional layers. We present parameterizations for the convolutional kernels that produce update rules to maintain symmetry throughout the training. We apply this architecture to the sequential recommendation problem, the RNA secondary structure inference problem, and the protein contact map prediction problem, showing that the symmetric structured networks produce improved results using fewer numbers of machine parameters.