POPNASv3: a Pareto-Optimal Neural Architecture Search Solution for Image and Time Series Classification

TL;DR

POPNASv3 is an efficient neural architecture search method that finds optimal models for image and time series classification across various hardware setups, reducing computational costs while maintaining high accuracy.

Contribution

It introduces a Pareto-optimal NAS algorithm that adapts to different tasks and hardware, improving search efficiency without sacrificing model performance.

Findings

Achieves competitive accuracy on image and time series datasets.

Reduces search time by focusing on Pareto-optimal architectures.

Effectively adapts to diverse hardware environments.

Abstract

The automated machine learning (AutoML) field has become increasingly relevant in recent years. These algorithms can develop models without the need for expert knowledge, facilitating the application of machine learning techniques in the industry. Neural Architecture Search (NAS) exploits deep learning techniques to autonomously produce neural network architectures whose results rival the state-of-the-art models hand-crafted by AI experts. However, this approach requires significant computational resources and hardware investments, making it less appealing for real-usage applications. This article presents the third version of Pareto-Optimal Progressive Neural Architecture Search (POPNASv3), a new sequential model-based optimization NAS algorithm targeting different hardware environments and multiple classification tasks. Our method is able to find competitive architectures within large search spaces, while keeping a flexible structure and data processing pipeline to adapt to different tasks. The algorithm employs Pareto optimality to reduce the number of architectures sampled during the search, drastically improving the time efficiency without loss in accuracy. The experiments performed on images and time series classification datasets provide evidence that POPNASv3 can explore a large set of assorted operators and converge to optimal architectures suited for the type of data provided under different scenarios.