Contrastive Self-supervised Neural Architecture Search

TL;DR

This paper introduces a contrastive self-supervised neural architecture search method that reduces reliance on labeled data, lowers computational costs, and achieves state-of-the-art results in image classification.

Contribution

It presents a novel NAS algorithm leveraging contrastive self-supervised learning and SMBO-TPE to efficiently discover high-performance architectures with minimal labeled data.

Findings

Achieves state-of-the-art accuracy on benchmark datasets.

Reduces data labeling costs significantly.

Speeds up the architecture search process.

Abstract

This paper proposes a novel cell-based neural architecture search algorithm (NAS), which completely alleviates the expensive costs of data labeling inherited from supervised learning. Our algorithm capitalizes on the effectiveness of self-supervised learning for image representations, which is an increasingly crucial topic of computer vision. First, using only a small amount of unlabeled train data under contrastive self-supervised learning allow us to search on a more extensive search space, discovering better neural architectures without surging the computational resources. Second, we entirely relieve the cost for labeled data (by contrastive loss) in the search stage without compromising architectures' final performance in the evaluation phase. Finally, we tackle the inherent discrete search space of the NAS problem by sequential model-based optimization via the tree-parzen estimator (SMBO-TPE), enabling us to reduce the computational expense response surface significantly. An extensive number of experiments empirically show that our search algorithm can achieve state-of-the-art results with better efficiency in data labeling cost, searching time, and accuracy in final validation.