POPNASv3: a Pareto-Optimal Neural Architecture Search Solution for Image and Time Series Classification
This work addresses the computational inefficiency of NAS for real-world applications in image and time series classification, though it is incremental as an improved version of an existing method.
The authors tackled the high computational cost of Neural Architecture Search (NAS) by introducing POPNASv3, a sequential model-based optimization algorithm that uses Pareto optimality to reduce sampled architectures, achieving competitive accuracy while drastically improving time efficiency on image and time series classification datasets.
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.