Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science
This addresses the scalability issue for AI practitioners by enabling neural networks to scale beyond current limits, though it is incremental as it builds on existing network science concepts.
The paper tackles the problem of reducing the quadratic parameter count in fully-connected layers of artificial neural networks by proposing sparse evolutionary training, which evolves an initial sparse topology into a scale-free one during learning, achieving no decrease in accuracy on 15 datasets.
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 (Erdős-Rényi 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.