mlsanityData to 7 Oct 2026

Prior-Guided One-shot Neural Architecture Search

arXiv 2206.13329 ↗First posted 27 Jun 2022cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Neural architecture search methods seek optimal candidates with efficient weight-sharing supernet training. However, recent studies indicate poor ranking consistency about the performance between stand-alone architectures and shared-weight networks. In this paper, we present Prior-Guided One-shot NAS (PGONAS) to strengthen the ranking correlation of supernets. Specifically, we first explore the effect of activation functions and propose a balanced sampling strategy based on the Sandwich Rule to alleviate weight coupling in the supernet. Then, FLOPs and Zen-Score are adopted to guide the training of supernet with ranking correlation loss. Our PGONAS ranks 3rd place in the supernet Track Track of CVPR2022 Second lightweight NAS challenge. Code is available in https://github.com/pprp/CVPR2022-NAS?competition-Track1-3th-solution.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 19 of its 31 references that are in the map. First posted on arXiv 27 Jun 2022.

Builds on

19 of 31 references.

References · 19

  1. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  2. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 831
  3. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 778
  4. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 666
  5. 2018Object Detection with Deep Learning: A Reviewcited by 524
  6. 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 480
  7. 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 411
  8. 2019Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentationcited by 258
  9. 2020Neural Architecture Search without Trainingcited by 241
  10. 2020BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Modelscited by 187
  11. 2021Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspectivecited by 168
  12. 2019FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Searchcited by 129
7 more
  1. 2020NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Sizecited by 98
  2. 2021Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognitioncited by 71
  3. 2019One-Shot Neural Architecture Search via Self-Evaluated Template Networkcited by 69
  4. 2018BlockQNN: Efficient Block-wise Neural Network Architecture Generationcited by 31
  5. 2021Learning Efficient, Explainable and Discriminative Representations for Pulmonary Nodules Classificationcited by 7
  6. 2019Balanced One-shot Neural Architecture Optimizationcited by 6
  7. 2021Improving Ranking Correlation of Supernet with Candidates Enhancement and Progressive Trainingcited by 2

Built on by

Cited by year

Citing papers per year: 2023: 9; 2024: 2; 2025: 1.

12 papers.

  1. 2024Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for Large Language Modelscited by 40
  2. 2023DisWOT: Student Architecture Search for Distillation WithOut Trainingcited by 29
  3. 2023DEHRFormer: Real-time Transformer for Depth Estimation and Haze Removal from Varicolored Haze Scenescited by 9
  4. 2023GP-NAS-ensemble: a model for NAS Performance Predictioncited by 7
  5. 2023RD-NAS: Enhancing One-shot Supernet Ranking Ability via Ranking Distillation from Zero-cost Proxiescited by 7
  6. 2023Pruning Large Language Models via Accuracy Predictorcited by 5
  7. 2024Efficiently Distilling LLMs for Edge Applicationscited by 5
  8. 2023Transfer-Once-For-All: AI Model Optimization for Edgecited by 4
  9. 2023InstaTune: Instantaneous Neural Architecture Search During Fine-Tuningcited by 4
  10. 2023TVT: Training-Free Vision Transformer Search on Tiny Datasetscited by 3
  11. 2023A Survey on Recent Teacher-student Learning Studiescited by 1
  12. 2025W-PCA Based Gradient-Free Proxy for Efficient Search of Lightweight Language Modelscited by 1