A Hybrid Performance Estimation Strategy for Optimizing Neural Architecture Search

Lei Zhang, Xiawu Zheng, Jiarui Wu, Xiang Chang, Nigel Copner, Chih-Min Lin, Fei Chao, Yanjie Chen, Changjing Shang, Qiang Shen

Allbwn ymchwil: Pennod mewn Llyfr/Adroddiad/Trafodion CynhadleddTrafodion Cynhadledd (Nid-Cyfnodolyn fathau)

11 Wedi eu Llwytho i Lawr (Pure)

Crynodeb

The emergence of neural architecture search (NAS) technology has lowered the professional threshold for optimizing model architectures. However, existing NAS methods primarily evaluate performance by fully training a network architecture, which is computationally expensive and slow. This paper proposes a hybrid performance estimation strategy search framework for neural architecture search, which can flexibly adjust the performance evaluation strategy at each stage. In the initial stage, this study uses less accurate but low-cost methods to quickly eliminate suboptimal architectures. As the search progresses, more computationally intensive but accurate evaluation strategies are employed to filter out the optimal network architectures. In the final stage, more precise verification is conducted to ensure that the selected network architecture achieves the best performance in practice. This research can adapt to different precision and speed requirements, providing flexible reduction space ratio strategies aimed at meeting accuracy requirements while maintaining efficiency. Its generalizability and flexibility help address various NAS challenges. Experimental results show that the method proposed in this study performs excellently in multiple benchmark tests, achieving a balance between performance and efficiency. Additionally, by testing on other search spaces, datasets, and tasks, this study demonstrates its good generalization ability.
Iaith wreiddiolSaesneg
TeitlUKCI 2024: 23rd UK Workshop on Computational Intelligence
StatwsCyhoeddwyd - 24 Gorff 2024
Digwyddiad23rd UK Workshop on Computational Intelligence and 8th International Conference on Belief Functions (BELIEF 2024) - Belfast Campus, Ulster University, Belfast, Teyrnas Unedig Prydain Fawr a Gogledd Iwerddon
Hyd: 04 Medi 202406 Medi 2024

Cynhadledd

Cynhadledd23rd UK Workshop on Computational Intelligence and 8th International Conference on Belief Functions (BELIEF 2024)
Teitl crynoUKCI 2024
Gwlad/TiriogaethTeyrnas Unedig Prydain Fawr a Gogledd Iwerddon
DinasBelfast
Cyfnod04 Medi 202406 Medi 2024

Ôl bys

Gweld gwybodaeth am bynciau ymchwil 'A Hybrid Performance Estimation Strategy for Optimizing Neural Architecture Search'. Gyda’i gilydd, maen nhw’n ffurfio ôl bys unigryw.

Dyfynnu hyn