Neural Architecture Search as Multiobjective Optimization Benchmarks: Problem Formulation and Performance Assessment

Lu Z, Cheng R, Jin Y, Tan KC, Deb K (2023)
IEEE Transactions on Evolutionary Computation: 1-1.

Zeitschriftenaufsatz | E-Veröff. vor dem Druck | Englisch
 
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Autor*in
Lu, Zhichao; Cheng, Ran; Jin, YaochuUniBi ; Tan, Kay Chen; Deb, Kalyanmoy
Abstract / Bemerkung
The ongoing advancements in network architecture design have led to remarkable achievements in deep learning across various challenging computer vision tasks. Meanwhile, the development of neural architecture search (NAS) has provided promising approaches to automating the design of network architectures for lower prediction error. Recently, the emerging application scenarios of deep learning (e.g., autonomous driving) have raised higher demands for network architectures considering multiple design criteria: number of parameters/weights, number of floating-point operations, inference latency, among others. From an optimization point of view, the NAS tasks involving multiple design criteria are intrinsically multiobjective optimization problems; hence, it is reasonable to adopt evolutionary multiobjective optimization (EMO) algorithms for tackling them. Nonetheless, there is still a clear gap confining the related research along this pathway: on the one hand, there is a lack of a general problem formulation of NAS tasks from an optimization point of view; on the other hand, there are challenges in conducting benchmark assessments of EMO algorithms on NAS tasks. To bridge the gap: (i) we formulate NAS tasks into general multi-objective optimization problems and analyze the complex characteristics from an optimization point of view; (ii) we present an end-to-end pipeline, dubbed EvoXBench, to generate benchmark test problems for EMO algorithms to run efficiently -without the requirement of GPUs or Pytorch/Tensorflow; (iii) we instantiate two test suites comprehensively covering two datasets, seven search spaces, and three hardware devices, involving up to eight objectives. Based on the above, we validate the proposed test suites using six representative EMO algorithms and provide some empirical analyses. The code of EvoXBench is available at https://github.com/EMI-Group/EvoXBench.
Erscheinungsjahr
2023
Zeitschriftentitel
IEEE Transactions on Evolutionary Computation
Seite(n)
1-1
ISSN
1089-778X
eISSN
1941-0026
Page URI
https://pub.uni-bielefeld.de/record/2978327

Zitieren

Lu Z, Cheng R, Jin Y, Tan KC, Deb K. Neural Architecture Search as Multiobjective Optimization Benchmarks: Problem Formulation and Performance Assessment. IEEE Transactions on Evolutionary Computation. 2023:1-1.
Lu, Z., Cheng, R., Jin, Y., Tan, K. C., & Deb, K. (2023). Neural Architecture Search as Multiobjective Optimization Benchmarks: Problem Formulation and Performance Assessment. IEEE Transactions on Evolutionary Computation, 1-1. https://doi.org/10.1109/TEVC.2022.3233364
Lu, Zhichao, Cheng, Ran, Jin, Yaochu, Tan, Kay Chen, and Deb, Kalyanmoy. 2023. “Neural Architecture Search as Multiobjective Optimization Benchmarks: Problem Formulation and Performance Assessment”. IEEE Transactions on Evolutionary Computation, 1-1.
Lu, Z., Cheng, R., Jin, Y., Tan, K. C., and Deb, K. (2023). Neural Architecture Search as Multiobjective Optimization Benchmarks: Problem Formulation and Performance Assessment. IEEE Transactions on Evolutionary Computation, 1-1.
Lu, Z., et al., 2023. Neural Architecture Search as Multiobjective Optimization Benchmarks: Problem Formulation and Performance Assessment. IEEE Transactions on Evolutionary Computation, , p 1-1.
Z. Lu, et al., “Neural Architecture Search as Multiobjective Optimization Benchmarks: Problem Formulation and Performance Assessment”, IEEE Transactions on Evolutionary Computation, 2023, pp. 1-1.
Lu, Z., Cheng, R., Jin, Y., Tan, K.C., Deb, K.: Neural Architecture Search as Multiobjective Optimization Benchmarks: Problem Formulation and Performance Assessment. IEEE Transactions on Evolutionary Computation. 1-1 (2023).
Lu, Zhichao, Cheng, Ran, Jin, Yaochu, Tan, Kay Chen, and Deb, Kalyanmoy. “Neural Architecture Search as Multiobjective Optimization Benchmarks: Problem Formulation and Performance Assessment”. IEEE Transactions on Evolutionary Computation (2023): 1-1.

Link(s) zu Volltext(en)
Access Level
Restricted Closed Access

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar