EUVIMEDEUVIMED entdecken
Crossref

PRE-NAS: Evolutionary Neural Architecture Search With Predictor

Yameng Peng, Andy Song, Vic Ciesielski, Haytham M. Fayek, Xiaojun Chang

IEEE Transactions on Evolutionary Computation · 2023-02 · 27 (1) · 26-36

DOI: 10.1109/tevc.2022.3227562 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Evolutionary Computation, 2023-02. Verfasst von Yameng Peng und 4 weiteren Autor:innen. Die Arbeit wurde bisher 44-mal zitiert (Crossref) und nennt 53 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Neural architecture search (NAS) aims to automate architecture engineering in neural networks. This often requires a high computational overhead to evaluate a number of candidate networks from the set of all possible networks in the search space. Prediction of the performance of a network can alleviate this high computational overhead by mitigating the need for evaluating every candidate network. Developing such a predictor typically requires a large number of evaluated architectures which may be difficult to obtain. We address this challenge by proposing a novel evolutionary-based NAS strategy, predictor-assisted evolutionary NAS (PRE-NAS) which can perform well even with an extremely small number of evaluated architectures. PRE-NAS leverages new evolutionary search strategies and integrates high-fidelity weight inheritance over generations. Unlike one-shot strategies, which may suffer from bias in the evaluation due to weight sharing, offspring candidates in PRE-NAS are topologically homogeneous. This circumvents bias and leads to more accurate predictions. Extensive experiments on the NAS-Bench-201 and DARTS search spaces show that PRE-NAS can outperform state-of-the-art NAS methods. With only a single GPU searching for 0.6 days, a competitive architecture can be found by PRE-NAS which achieves 2.40% and 24% test error rates on CIFAR-10 and ImageNet, respectively.

Zitieren

APA

Peng, Y., Song, A., Ciesielski, V., Fayek, H. M., & Chang, X. (2023). PRE-NAS: Evolutionary Neural Architecture Search With Predictor. IEEE Transactions on Evolutionary Computation, 27(1), 26-36. https://doi.org/10.1109/tevc.2022.3227562

Vancouver

Peng Y, Song A, Ciesielski V, Fayek HM, Chang X. PRE-NAS: Evolutionary Neural Architecture Search With Predictor. IEEE Transactions on Evolutionary Computation. 2023;27(1):26-36. doi:10.1109/tevc.2022.3227562

BibTeX
@article{Peng2023,
  author = {Peng, Yameng and Song, Andy and Ciesielski, Vic and Fayek, Haytham M. and Chang, Xiaojun},
  title = {PRE-NAS: Evolutionary Neural Architecture Search With Predictor},
  journal = {IEEE Transactions on Evolutionary Computation},
  year = {2023},
  volume = {27},
  number = {1},
  pages = {26--36},
  doi = {10.1109/tevc.2022.3227562}
}
Kostenlos starten →