A Pairwise Comparison Relation-assisted Multi-objective Evolutionary Neural Architecture Search Method with Multi-population Mechanism

TL;DR

This paper introduces SMEMNAS, a multi-objective evolutionary neural architecture search method that uses pairwise comparison relations and a multi-population mechanism to efficiently discover high-performance, multi-criteria optimized neural networks with reduced computational resources.

Contribution

The paper proposes a novel NAS approach combining pairwise comparison-based surrogate modeling and a multi-population mechanism for efficient multi-objective optimization.

Findings

Achieves 78.91% accuracy on ImageNet with 570M MAdds using only one GPU in 0.17 days.

Effectively balances multiple objectives beyond accuracy, such as efficiency and compactness.

Demonstrates superior search efficiency and performance compared to existing NAS methods.

Abstract

Neural architecture search (NAS) has emerged as a powerful paradigm that enables researchers to automatically explore vast search spaces and discover efficient neural networks. However, NAS suffers from a critical bottleneck, i.e. the evaluation of numerous architectures during the search process demands substantial computing resources and time. In order to improve the efficiency of NAS, a series of methods have been proposed to reduce the evaluation time of neural architectures. However, they are not efficient enough and still only focus on the accuracy of architectures. Beyond classification accuracy, real-world applications increasingly demand more efficient and compact network architectures that balance multiple performance criteria. To address these challenges, we propose the SMEMNAS, a pairwise comparison relation-assisted multi-objective evolutionary algorithm based on a multi-population mechanism. In the SMEMNAS, a surrogate model is constructed based on pairwise comparison relations to predict the accuracy ranking of architectures, rather than the absolute accuracy. Moreover, two populations cooperate with each other in the search process, i.e. a main population that guides the evolutionary process, while a vice population that enhances search diversity. Our method aims to discover high-performance models that simultaneously optimize multiple objectives. We conduct comprehensive experiments on CIFAR-10, CIFAR-100 and ImageNet datasets to validate the effectiveness of our approach. With only a single GPU searching for 0.17 days, competitive architectures can be found by SMEMNAS which achieves 78.91% accuracy with the MAdds of 570M on the ImageNet. This work makes a significant advancement in the field of NAS.