skip to main content
Idioma:
Tipo de recurso Mostra resultados com: Mostra resultados com: Índice

Ranking‐based architecture generation for surrogate‐assisted neural architecture search

Xiao, Songyi ; Wang, Wenjun

Concurrency and computation, 2024-05, Vol.36 (12), p.n/a [Periódico revisado por pares]

Hoboken: Wiley Subscription Services, Inc

Texto completo disponível

Citações Citado por
  • Título:
    Ranking‐based architecture generation for surrogate‐assisted neural architecture search
  • Autor: Xiao, Songyi ; Wang, Wenjun
  • Assuntos: generative model ; neural architecture search ; Neural networks ; Optimization ; ranker ; Ranking ; Representations ; Search methods ; surrogate‐assisted evolutionary algorithm ; Unsupervised learning
  • É parte de: Concurrency and computation, 2024-05, Vol.36 (12), p.n/a
  • Descrição: 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.
  • Editor: Hoboken: Wiley Subscription Services, Inc
  • Idioma: Inglês
Voltar para lista de resultados

  • Realização: ABCD-USP USP   Logos de Redes Sociais: Freepik

Buscando em bases de dados remotas. Favor aguardar.