mlsanityData to 14 Oct 2026

Improve Ranking Correlation of Super-net through Training Scheme from One-shot NAS to Few-shot NAS

arXiv 2206.05896 ↗First posted 13 Jun 2022cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

The algorithms of one-shot neural architecture search(NAS) have been widely used to reduce computation consumption. However, because of the interference among the subnets in which weights are shared, the subnets inherited from these super-net trained by those algorithms have poor consistency in precision ranking. To address this problem, we propose a step-by-step training super-net scheme from one-shot NAS to few-shot NAS. In the training scheme, we firstly train super-net in a one-shot way, and then we disentangle the weights of super-net by splitting them into multi-subnets and training them gradually. Finally, our method ranks 4th place in the CVPR2022 3rd Lightweight NAS Challenge Track1. Our code is available at https://github.com/liujiawei2333/CVPR2022-NAS-competition-Track-1-4th-solution.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 12 of its 13 references that are in the map. First posted on arXiv 13 Jun 2022.

Builds on

12 of 13 references.

References · 12

  1. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 787
  2. 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 414
  3. 2020BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Modelscited by 188
  4. 2019FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Searchcited by 130
  5. 2020Few-shot Neural Architecture Searchcited by 50
  6. 2022Generalizing Few-Shot NAS with Gradient Matchingcited by 25
  7. 2020Deeper Insights into Weight Sharing in Neural Architecture Searchcited by 24
  8. 2021K-shot NAS: Learnable Weight-Sharing for NAS with K-shot Supernetscited by 22
  9. 2021Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shiftcited by 14
  10. 2021Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture Searchcited by 8
  11. 2020How Does Supernet Help in Neural Architecture Search?cited by 5
  12. 2021Improving Ranking Correlation of Supernet with Candidates Enhancement and Progressive Trainingcited by 2

Built on by

Cited by year

Citing papers per year: 2023: 1.

1 paper.

  1. 2023Balanced Mixture of SuperNets for Learning the CNN Pooling Architecturecited by 1