Towards evolution of Deep Neural Networks through contrastive Self-Supervised learning

TL;DR

This paper explores how neuroevolution combined with self-supervised learning can automate DNN design and reduce dependence on labeled data, achieving competitive performance on CIFAR-10.

Contribution

It introduces a framework that evolves neural networks using self-supervised learning, bridging the gap to supervised learning in performance and data reliance.

Findings

Evolved networks perform well on CIFAR-10 with less labeled data.

Self-supervised learning reduces the impact of labeled data on network structure.

The structure of networks learned via self-supervised methods is less affected by the amount of labeled data.

Abstract

Deep Neural Networks (DNNs) have been successfully applied to a wide range of problems. However, two main limitations are commonly pointed out. The first one is that they require long time to design. The other is that they heavily rely on labelled data, which can sometimes be costly and hard to obtain. In order to address the first problem, neuroevolution has been proved to be a plausible option to automate the design of DNNs. As for the second problem, self-supervised learning has been used to leverage unlabelled data to learn representations. Our goal is to study how neuroevolution can help self-supervised learning to bridge the gap to supervised learning in terms of performance. In this work, we propose a framework that is able to evolve deep neural networks using self-supervised learning. Our results on the CIFAR-10 dataset show that it is possible to evolve adequate neural networks while reducing the reliance on labelled data. Moreover, an analysis to the structure of the evolved networks suggests that the amount of labelled data fed to them has less effect on the structure of networks that learned via self-supervised learning, when compared to individuals that relied on supervised learning.