EUVIMEDEUVIMED entdecken
Crossref

Pareto-Wise Ranking Classifier for Multiobjective Evolutionary Neural Architecture Search

Lianbo Ma, Nan Li, Guo Yu, Xiaoyu Geng, Shi Cheng, Xingwei Wang, Min Huang, Yaochu Jin

IEEE Transactions on Evolutionary Computation · 2024-06 · 28 (3) · 570-581

DOI: 10.1109/tevc.2023.3314766 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Evolutionary Computation, 2024-06. Verfasst von Lianbo Ma und 7 weiteren Autor:innen. Die Arbeit wurde bisher 103-mal zitiert (Crossref) und nennt 65 Literaturangaben. Gefördert von: NSFC Key Supported Project of the Major Research Plan, National Natural Science Foundation of China, National Key Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In multiobjective evolutionary neural architecture search (NAS), existing predictor-based methods commonly suffer from the rank disorder issue that a candidate high-performance architecture may have a poor ranking compared with the worse architecture in terms of the trained predictor. To alleviate the above issue, we aim to train a Pareto-wise end-to-end ranking classifier to simplify the architecture search process by transforming the complex multiobjective NAS task into a simple classification task. To this end, a classifier-based Pareto evolution approach is proposed, where an online classifier is trained to directly predict the dominance relationship between the candidate and reference architectures. Besides, an adaptive clustering method is designed to select reference architectures for the classifier, and an $\alpha $ -domination-assisted approach is developed to address the imbalance issue of positive and negative samples. The proposed approach is compared with a number of state-of-the-art NAS methods on widely used test datasets, and computation results show that the proposed approach is able to alleviate the rank disorder issue and outperforms other methods. Especially, the proposed method is able to find a set of promising network architectures with different model sizes ranging from 2M to 5M under diverse objectives and constraints.

Förderung

  • NSFC Key Supported Project of the Major Research Plan
  • National Natural Science Foundation of China
  • National Key Research and Development Program of China
  • Fundamental Research Funds for the Central Universities
  • China Postdoctoral Science Foundation

Zitieren

APA

Ma, L., Li, N., Yu, G., Geng, X., Cheng, S., Wang, X., Huang, M., & Jin, Y. (2024). Pareto-Wise Ranking Classifier for Multiobjective Evolutionary Neural Architecture Search. IEEE Transactions on Evolutionary Computation, 28(3), 570-581. https://doi.org/10.1109/tevc.2023.3314766

Vancouver

Ma L, Li N, Yu G, Geng X, Cheng S, Wang X, et al. Pareto-Wise Ranking Classifier for Multiobjective Evolutionary Neural Architecture Search. IEEE Transactions on Evolutionary Computation. 2024;28(3):570-581. doi:10.1109/tevc.2023.3314766

BibTeX
@article{Ma2024,
  author = {Ma, Lianbo and Li, Nan and Yu, Guo and Geng, Xiaoyu and Cheng, Shi and Wang, Xingwei and Huang, Min and Jin, Yaochu},
  title = {Pareto-Wise Ranking Classifier for Multiobjective Evolutionary Neural Architecture Search},
  journal = {IEEE Transactions on Evolutionary Computation},
  year = {2024},
  volume = {28},
  number = {3},
  pages = {570--581},
  doi = {10.1109/tevc.2023.3314766}
}
Kostenlos starten →