Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science

TL;DR

This paper introduces a method for training sparse neural networks that evolve their connectivity to a scale-free topology, significantly reducing parameters without sacrificing accuracy, thus enabling scalable deep learning.

Contribution

It proposes a novel sparse evolutionary training algorithm that transforms initial random sparse layers into scale-free networks during learning, improving scalability.

Findings

Reduces network parameters quadratically with no accuracy loss.

Effective across various neural network architectures and datasets.

Potential to enable larger, more scalable neural networks.

Abstract

Through the success of deep learning in various domains, artificial neural networks are currently among the most used artificial intelligence methods. Taking inspiration from the network properties of biological neural networks (e.g. sparsity, scale-freeness), we argue that (contrary to general practice) artificial neural networks, too, should not have fully-connected layers. Here we propose sparse evolutionary training of artificial neural networks, an algorithm which evolves an initial sparse topology (Erd\H{o}s-R\'enyi random graph) of two consecutive layers of neurons into a scale-free topology, during learning. Our method replaces artificial neural networks fully-connected layers with sparse ones before training, reducing quadratically the number of parameters, with no decrease in accuracy. We demonstrate our claims on restricted Boltzmann machines, multi-layer perceptrons, and convolutional neural networks for unsupervised and supervised learning on 15 datasets. Our approach has the potential to enable artificial neural networks to scale up beyond what is currently possible.