• Home
  • Search
  • Multi-Objective Evolutionary Neural Architecture Search with Weight-Sharing Supernet
  • Cite Icon5
  • https://doi.org/10.3390/app14146143Copy DOI Icon

Multi-Objective Evolutionary Neural Architecture Search with Weight-Sharing Supernet

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Deep neural networks have played a crucial role in the field of deep learning, achieving significant success in practical applications. The architecture of neural networks is key to their performance. In the past few years, these architectures have been manually designed by experts with rich domain knowledge. Additionally, the optimal neural network architecture can vary depending on specific tasks and data distributions. Neural Architecture Search (NAS) is a class of techniques aimed at automatically searching for and designing neural network architectures according to the given tasks and data. Specifically, evolutionary-computation-based NAS methods are known for their strong global search capability and have aroused widespread interest in recent years. Although evolutionary-computation-based NAS has achieved success in a wide range of research and applications, it still faces bottlenecks in training and evaluating a large number of individuals during optimization. In this study, we first devise a multi-objective evolutionary NAS framework based on a weight-sharing supernet to improve the search efficiency of traditional evolutionary-computation-based NAS. This framework combines the population optimization characteristic of evolutionary algorithms with the weight-sharing ideas in one-shot models. We then design a bi-population MOEA/D algorithm based on the proposed framework to effectively solve the NAS problem. By constructing two sub-populations with different optimization objectives, the algorithm can effectively explore network architectures of various sizes in complex search spaces. An inter-population communication mechanism further enhances the algorithm’s exploratory capability, enabling it to find network architectures with uniform distribution and high diversity. Finally, we conduct performance comparison experiments on image classification datasets of different scales and complexities. Experimental results demonstrate the effectiveness of the proposed multi-objective evolutionary NAS framework and the practicality and transferability of the introduced bi-population MOEA/D-based NAS method compared to existing state-of-the-art NAS methods.

Loading PDF

Similar Papers
  • Book Chapter
  • Citations1

Comparative Analysis of Neural Architecture Search Methods for Classification of Cultural Heritage Sites

  • Jan 01, 2022
  • Sunil V Gurlahosur +8
  • Research Article
  • Citations6

BossNAS Family: Block-Wisely Self-Supervised Neural Architecture Search.

  • May 01, 2025
  • IEEE transactions on pattern analysis and machine intelligence
  • Changlin Li +6
  • Conference Article
  • Citations48

Evolutionary Neural Architecture Search for Image Restoration

  • Jul 01, 2019
  • Gerard Jacques Van Wyk +1
  • Research Article
  • Citations5

Neural architecture search based on dual attention mechanism for image classification.

  • Jan 01, 2022
  • Mathematical Biosciences & Engineering
  • Cong Jin +3
  • Book Chapter
  • Citations1

Efficient Evolutionary Neural Architecture Search (NAS) by Modular Inheritable Crossover

  • Jan 01, 2020
  • Hao Tan +3
  • Book Chapter
  • Citations292

Single-Path NAS: Designing Hardware-Efficient ConvNets in Less Than 4 Hours

  • Jan 01, 2020
  • Dimitrios Stamoulis +6
  • Research Article
  • Citations12

A multi-perspective revisit to the optimization methods of Neural Architecture Search and Hyper-parameter optimization for non-federated and federated learning environments

  • Jul 20, 2023
  • Computers and Electrical Engineering
  • Salabat Khan +5
  • Research Article
  • Citations12

Enhanced Gradient for Differentiable Architecture Search.

  • Jul 01, 2024
  • IEEE transactions on neural networks and learning systems
  • Haichao Zhang +4
  • Book Chapter
  • Citations40

Resource Optimized Neural Architecture Search for 3D Medical Image Segmentation

  • Jan 01, 2019
  • Woong Bae +5
  • Conference Article
  • Citations19

Efficient Neural Architecture Search for End-to-End Speech Recognition Via Straight-Through Gradients

  • Jan 19, 2021
  • Huahuan Zheng +2
  • Research Article
  • Citations22

EAT-NAS: elastic architecture transfer for accelerating large-scale neural architecture search

  • Aug 06, 2021
  • Science China Information Sciences
  • Jiemin Fang +7
  • Book Chapter
  • Citations15

Evolutionary Neural Architecture Search Supporting Approximate Multipliers

  • Jan 01, 2021
  • Michal Pinos +2
  • Conference Article
  • Citations8

Optimizing FPGA-Based CNN Accelerator Using Differentiable Neural Architecture Search

  • Oct 01, 2020
  • Hongxiang Fan +5
  • Research Article
  • Citations2

DDNAS: Discretized Differentiable Neural Architecture Search for Text Classification

  • Oct 03, 2023
  • ACM Transactions on Intelligent Systems and Technology
  • Kuan-Chun Chen +2
  • Research Article

Image-based prediction of soiling-induced power loss in solar panels: A novel neural architecture search method via reinforcement learning

  • May 01, 2026
  • Applied Energy
  • Md.Shadman Abid +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.