Ranking‐based architecture generation for surrogate‐assisted neural architecture search
Concurrency and Computation: Practice and Experience · 30.05.2024 · 36 (12)
DOI: 10.1002/cpe.8051 ↗Kurz gefasst
Fachartikel in der Zeitschrift Concurrency and Computation: Practice and Experience, online erschienen am 26.02.2024. Verfasst von Songyi Xiao und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 69 Literaturangaben. Gefördert von: Natural Science Foundation of Jiangxi Province.
Abstract (Originalsprache)
Architectures generation optimization has been received a lot of attention in neural architecture search (NAS) since its efficiency in generating architecture. By learning the architecture representation through unsupervised learning and constructing a latent space, the prediction process of predictors is simplified, leading to improved efficiency in architecture search. However, searching for architectures with top performance in complex and large NAS search spaces remains challenging. In this paper, an approach that combined a ranker and generative model is proposed to address this challenge through regularizing the latent space and identifying architectures with top rankings. We introduce the ranking error to gradually regulate the training of the generative model, making it easier to identify architecture representations in the latent space. Additionally, a surrogate‐assisted evolutionary search method that utilized neural network Bayesian optimization is proposed to efficiently explore promising architectures in the latent space. We demonstrate the benefits of our approach in optimizing architectures with top rankings, and our method outperforms state‐of‐the‐art techniques on various NAS benchmarks. The code is available at https://github.com/outofstyle/RAGS‐NAS .
Förderung
- Natural Science Foundation of Jiangxi Province
Zitieren
APA
Xiao, S., & Wang, W. (2024). Ranking‐based architecture generation for surrogate‐assisted neural architecture search. Concurrency and Computation: Practice and Experience, 36(12). https://doi.org/10.1002/cpe.8051
Vancouver
Xiao S, Wang W. Ranking‐based architecture generation for surrogate‐assisted neural architecture search. Concurrency and Computation: Practice and Experience. 2024;36(12). doi:10.1002/cpe.8051
BibTeX
@article{Xiao2024,
author = {Xiao, Songyi and Wang, Wenjun},
title = {Ranking‐based architecture generation for surrogate‐assisted neural architecture search},
journal = {Concurrency and Computation: Practice and Experience},
year = {2024},
volume = {36},
number = {12},
doi = {10.1002/cpe.8051}
}
EUVIMED