Idioma:

A Generic Graph-Based Neural Architecture Encoding Scheme for Predictor-Based NAS

Vedaldi, Andrea ; Bischof, Horst ; Brox, Thomas ; Frahm, Jan-Michael

Computer Vision - ECCV 2020, 2020, Vol.12358, p.189-204 [Periódico revisado por pares]

Sem texto completo

Citações Citado por

Título:
A Generic Graph-Based Neural Architecture Encoding Scheme for Predictor-Based NAS
Autor: Vedaldi, Andrea ; Bischof, Horst ; Brox, Thomas ; Frahm, Jan-Michael
Assuntos: Neural architecture search (NAS) ; Predictor-based NAS
É parte de: Computer Vision - ECCV 2020, 2020, Vol.12358, p.189-204
Notas: Electronic supplementary materialThe online version of this chapter (https://doi.org/10.1007/978-3-030-58601-0_12) contains supplementary material, which is available to authorized users.
Descrição: This work proposes a novel Graph-based neural ArchiTecture Encoding Scheme, a.k.a. GATES, to improve the predictor-based neural architecture search. Specifically, different from existing graph-based schemes, GATES models the operations as the transformation of the propagating information, which mimics the actual data processing of neural architecture. GATES is a more reasonable modeling of the neural architectures, and can encode architectures from both the “operation on node” and “operation on edge” cell search spaces consistently. Experimental results on various search spaces confirm GATES’s effectiveness in improving the performance predictor. Furthermore, equipped with the improved performance predictor, the sample efficiency of the predictor-based neural architecture search (NAS) flow is boosted.
Títulos relacionados: Lecture Notes in Computer Science
Editor: Switzerland: Springer International Publishing AG
Idioma: Inglês

Voltar para lista de resultados