EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Search

TL;DR

EPE-NAS introduces a rapid, training-free performance estimation method for neural architecture search that correlates untrained network scores with trained performance, significantly reducing search time.

Contribution

It proposes a novel, training-free performance estimation strategy that can be integrated into various NAS methods to accelerate the search process.

Findings

EPE-NAS achieves robust correlation between untrained and trained network performance.

Networks can be searched in seconds on a single GPU without training.

The method is compatible with multiple NAS strategies.

Abstract

Neural Architecture Search (NAS) has shown excellent results in designing architectures for computer vision problems. NAS alleviates the need for human-defined settings by automating architecture design and engineering. However, NAS methods tend to be slow, as they require large amounts of GPU computation. This bottleneck is mainly due to the performance estimation strategy, which requires the evaluation of the generated architectures, mainly by training them, to update the sampler method. In this paper, we propose EPE-NAS, an efficient performance estimation strategy, that mitigates the problem of evaluating networks, by scoring untrained networks and creating a correlation with their trained performance. We perform this process by looking at intra and inter-class correlations of an untrained network. We show that EPE-NAS can produce a robust correlation and that by incorporating it into a simple random sampling strategy, we are able to search for competitive networks, without requiring any training, in a matter of seconds using a single GPU. Moreover, EPE-NAS is agnostic to the search method, since it focuses on the evaluation of untrained networks, making it easy to integrate into almost any NAS method.