M2M-Net: multi-objective neural architecture search using dynamic M2M population decomposition

Evolutionary multi-objective neural architecture search (MO-NAS) is an efficient solution for automating the design of deep neural network architectures, aiming to explore a diverse range of objectives. However, the sensitivity of objectives in MO-NAS varies over generations, leading to a search imb...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Neural computing & applications Ročník 37; číslo 27; s. 22473 - 22491
Hlavní autoři: Tan, Zhiwen, Guo, Daqi, Chen, Junan, Chen, Lei
Médium: Journal Article
Jazyk:angličtina
Vydáno: London Springer London 01.09.2025
Springer Nature B.V
Témata:
Artificial Intelligence
Artificial neural networks
Classification
Combinatorial analysis
Computational Biology/Bioinformatics
Computational Science and Engineering
Computer Science
Computing costs
Data Mining and Knowledge Discovery
Decomposition
Design
Evolutionary algorithms
Genetic algorithms
Human performance
Image Processing and Computer Vision
Multiple objective analysis
Neural networks
Objectives
Optimization
Pareto optimum
Probability and Statistics in Computer Science
S.I.: Hybrid Approaches to Nature-inspired Optimization Algorithms and Their Applications
Searching
Special Issue on Hybrid Approaches to Nature-inspired Optimization Algorithms and Their Applications
Search imbalance
Population decomposition
Neural architecture search (NAS)
Evolutionary multi-objective optimization
ISSN:0941-0643, 1433-3058
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Evolutionary multi-objective neural architecture search (MO-NAS) is an efficient solution for automating the design of deep neural network architectures, aiming to explore a diverse range of objectives. However, the sensitivity of objectives in MO-NAS varies over generations, leading to a search imbalance, and local search plays a crucial role in this combinatorial optimization problem with a discrete search space. In this paper, we propose M2M-Net, a dynamic self-adaptive (Multi-objective to Multi-objective) M2M population decomposition-based evolutionary algorithm for NAS. M2M-Net leverages dynamic self-adaptive M2M population decomposition to overcome the search imbalance in MO-NAS. The subpopulation-based search within M2M-Net facilitates local search through crossover and mutation. Additionally, M2M-Net incorporates a proxy model to reduce computational cost in architecture evaluation and utilizes the channel attention mechanism to improve the accuracy of proxy model evaluation. Experimental studies on CIFAR-10 and CIFAR-100 datasets validate the effectiveness and efficiency of M2M-Net. Comparisons and analysis demonstrate that M2M-Net achieves comparable performance to state-of-the-art NAS methods while utilizing fewer computational resources.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0941-0643
1433-3058
DOI:10.1007/s00521-024-10595-3