Towards evolution of Deep Neural Networks through contrastive Self-Supervised learning
This work addresses the need for more efficient and data-efficient neural network design, though it appears incremental as it combines existing neuroevolution and self-supervised learning approaches.
The paper tackled the problem of automating deep neural network design and reducing reliance on labeled data by proposing a framework that evolves networks using self-supervised learning, with results on CIFAR-10 showing it can evolve adequate networks while decreasing labeled data dependency.
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.