Population-based guiding for evolutionary neural architecture search

Dendorfer S, Kist A (2025)


Publication Type: Journal article

Publication year: 2025

Journal

Book Volume: 15

Article Number: 38996

Journal Issue: 1

DOI: 10.1038/s41598-025-25840-5

Abstract

Neural Architecture Search (NAS)—combined with biology-inspired evolutionary methods—can help discover suitable architectures tailored to a given objective. A guided evolutionary approach can enhance efficiency, aiming to accelerate the discovery of top-performing architectures within a given search space. We propose a novel algorithmic framework that implements selection, crossover, and mutation operations to generate new candidate architectures during an evolutionary Neural Architecture Search: A greedy selection operator, relying solely on model accuracy data, promotes exploitation. Incorporating architecture embeddings to further refine the mutation process enhances exploration. We introduce a guided mutation approach to steer the search toward unexplored regions of the current population. The proposed strategy, PBG (Population-Based Guiding), synergizes both explorative and exploitative methods. It substantially outperforms baseline methods such as regularized evolution by being up to three times faster on NAS-Bench-101. This combined approach not only leverages the strengths of both explorative guided mutation and exploitative greedy selection strategies, but also provides a robust and efficient framework reaching competitive performance for evolutionary Neural Architecture Search across benchmarks.

Authors with CRIS profile

How to cite

APA:

Dendorfer, S., & Kist, A. (2025). Population-based guiding for evolutionary neural architecture search. Scientific Reports, 15(1). https://doi.org/10.1038/s41598-025-25840-5

MLA:

Dendorfer, Stefan, and Andreas Kist. "Population-based guiding for evolutionary neural architecture search." Scientific Reports 15.1 (2025).

BibTeX: Download