Meta knowledge assisted Evolutionary Neural Architecture Search

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Yangyang, Liu, Guanlong, Shang, Ronghua, Jiao, Licheng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916714862608384
author Li, Yangyang
Liu, Guanlong
Shang, Ronghua
Jiao, Licheng
author_facet Li, Yangyang
Liu, Guanlong
Shang, Ronghua
Jiao, Licheng
contents Evolutionary computation (EC)-based neural architecture search (NAS) has achieved remarkable performance in the automatic design of neural architectures. However, the high computational cost associated with evaluating searched architectures poses a challenge for these methods, and a fixed form of learning rate (LR) schedule means greater information loss on diverse searched architectures. This paper introduces an efficient EC-based NAS method to solve these problems via an innovative meta-learning framework. Specifically, a meta-learning-rate (Meta-LR) scheme is used through pretraining to obtain a suitable LR schedule, which guides the training process with lower information loss when evaluating each individual. An adaptive surrogate model is designed through an adaptive threshold to select the potential architectures in a few epochs and then evaluate the potential architectures with complete epochs. Additionally, a periodic mutation operator is proposed to increase the diversity of the population, which enhances the generalizability and robustness. Experiments on CIFAR-10, CIFAR-100, and ImageNet1K datasets demonstrate that the proposed method achieves high performance comparable to that of many state-of-the-art peer methods, with lower computational cost and greater robustness.
format Preprint
id arxiv_https___arxiv_org_abs_2504_21545
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Meta knowledge assisted Evolutionary Neural Architecture Search
Li, Yangyang
Liu, Guanlong
Shang, Ronghua
Jiao, Licheng
Neural and Evolutionary Computing
Artificial Intelligence
Evolutionary computation (EC)-based neural architecture search (NAS) has achieved remarkable performance in the automatic design of neural architectures. However, the high computational cost associated with evaluating searched architectures poses a challenge for these methods, and a fixed form of learning rate (LR) schedule means greater information loss on diverse searched architectures. This paper introduces an efficient EC-based NAS method to solve these problems via an innovative meta-learning framework. Specifically, a meta-learning-rate (Meta-LR) scheme is used through pretraining to obtain a suitable LR schedule, which guides the training process with lower information loss when evaluating each individual. An adaptive surrogate model is designed through an adaptive threshold to select the potential architectures in a few epochs and then evaluate the potential architectures with complete epochs. Additionally, a periodic mutation operator is proposed to increase the diversity of the population, which enhances the generalizability and robustness. Experiments on CIFAR-10, CIFAR-100, and ImageNet1K datasets demonstrate that the proposed method achieves high performance comparable to that of many state-of-the-art peer methods, with lower computational cost and greater robustness.
title Meta knowledge assisted Evolutionary Neural Architecture Search
topic Neural and Evolutionary Computing
Artificial Intelligence
url https://arxiv.org/abs/2504.21545