• Home
  • Search
  • Enhanced Gradient for Differentiable Architecture Search.
  • Open Access IconOpen Access
  • Cite Icon12
  • https://doi.org/10.1109/tnnls.2023.3235479Copy DOI Icon

Enhanced Gradient for Differentiable Architecture Search.

Show More
  • Abstract
  • Literature Map
  • Citations
  • Similar Papers
Abstract

In recent years, neural architecture search (NAS) methods have been proposed for the automatic generation of task-oriented network architecture in image classification. However, the architectures obtained by existing NAS approaches are optimized only for classification performance and do not adapt to devices with limited computational resources. To address this challenge, we propose a neural network architecture search algorithm aiming to simultaneously improve the network performance and reduce the network complexity. The proposed framework automatically builds the network architecture at two stages: block-level search and network-level search. At the stage of block-level search, a gradient-based relaxation method is proposed, using an enhanced gradient to design high-performance and low-complexity blocks. At the stage of network-level search, an evolutionary multiobjective algorithm is utilized to complete the automatic design from blocks to the target network. The experimental results demonstrate that our method outperforms all evaluated hand-crafted networks in image classification, with an error rate of 3.18% on Canadian Institute for Advanced Research (CIFAR10) and an error rate of 19.16% on CIFAR100, both at network parameter size less than 1 M. Obviously, compared with other NAS methods, our method offers a tremendous reduction in designed network architecture parameters.

Similar Papers
  • Research Article
  • Citations15

Efficient and lightweight convolutional neural network architecture search methods for object classification

  • Jul 06, 2024
  • Pattern Recognition
  • Chuen-Horng Lin +3
  • 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
  • Book Chapter
  • Citations1

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

  • Jan 01, 2022
  • Sunil V Gurlahosur +8
  • Conference Article
  • Citations48

Evolutionary Neural Architecture Search for Image Restoration

  • Jul 01, 2019
  • Gerard Jacques Van Wyk +1
  • Book Chapter
  • Citations1

TF-MOPNAS: Training-free Multi-objective Pruning-Based Neural Architecture Search

  • Jan 01, 2022
  • Quan Minh Phan +1
  • Research Article
  • Citations5

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

  • Jan 01, 2022
  • Mathematical Biosciences & Engineering
  • Cong Jin +3
  • 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
  • PDF
  • Research Article
  • Citations3

Low Cost Evolutionary Neural Architecture Search (LENAS) Applied to Traffic Forecasting

  • Jul 28, 2023
  • Machine Learning and Knowledge Extraction
  • Daniel Klosa +1
  • Book Chapter
  • Citations1

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

  • Jan 01, 2020
  • Hao Tan +3
  • Book Chapter
  • Citations1

“Mini-Benchmarking” Approach to Optimize Evolutionary Methods of Neural Architecture Search

  • Jan 01, 2021
  • Kamil Khamitov +1
  • 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
  • PDF
  • Research Article
  • Citations5

Ancient mural dynasty recognition algorithm based on a neural network architecture search

  • May 15, 2024
  • Heritage Science
  • Jianfang Cao +4
  • Conference Article
  • Citations45

Prioritized Architecture Sampling with Monto-Carlo Tree Search

  • Jun 01, 2021
  • Xiu Su +7
  • Book Chapter
  • Citations15

Evolutionary Neural Architecture Search Supporting Approximate Multipliers

  • Jan 01, 2021
  • Michal Pinos +2
  • PDF
  • Research Article
  • Citations5

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

  • Jul 15, 2024
  • Applied Sciences
  • Junchao Liang +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.