mlsanityData to 7 Oct 2026

GP-NAS-ensemble: a model for NAS Performance Prediction

arXiv 2301.09231 ↗First posted 23 Jan 2023cs.LG stat.AP stat.MLcited by 7

Not on the map. Why?

Abstract (arXiv)

It is of great significance to estimate the performance of a given model architecture without training in the application of Neural Architecture Search (NAS) as it may take a lot of time to evaluate the performance of an architecture. In this paper, a novel NAS framework called GP-NAS-ensemble is proposed to predict the performance of a neural network architecture with a small training dataset. We make several improvements on the GP-NAS model to make it share the advantage of ensemble learning methods. Our method ranks second in the CVPR2022 second lightweight NAS challenge performance prediction track.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 28 of its 50 references that are in the map. First posted on arXiv 23 Jan 2023.

Builds on

28 of 50 references.

References · 28

  1. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  2. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  3. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
  4. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
  5. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
  6. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 902
  7. 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 411
  8. 2015Recent Advances in Convolutional Neural Networkscited by 360
  9. 2017Large-Scale Evolution of Image Classifierscited by 348
  10. 2018Neural Architecture Optimizationcited by 164
  11. 2017Genetic CNNcited by 124
  12. 2019Neural Predictor for Neural Architecture Searchcited by 116
16 more
  1. 2020BRP-NAS: Prediction-based NAS using GCNscited by 109
  2. 2019One-Shot Neural Architecture Search via Self-Evaluated Template Networkcited by 69
  3. 2020AttentiveNAS: Improving Neural Architecture Search via Attentive Samplingcited by 65
  4. 2021TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Searchcited by 57
  5. 2020A Generic Graph-based Neural Architecture Encoding Scheme for Predictor-based NAScited by 53
  6. 2019ReNAS:Relativistic Evaluation of Neural Architecture Searchcited by 35
  7. 2021Rapid Neural Architecture Search by Learning to Generate Graphs from Datasetscited by 33
  8. 2018Accurate, Data-Efficient, Unconstrained Text Recognition with Convolutional Neural Networkscited by 31
  9. 2021Stronger NAS with Weaker Predictorscited by 28
  10. 2018You Only Search Once: Single Shot Neural Architecture Search via Direct Sparse Optimizationcited by 23
  11. 2019Continual and Multi-Task Architecture Searchcited by 22
  12. 2018Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Searchcited by 19
  13. 2018NSGA-Net: Neural Architecture Search using Multi-Objective Genetic Algorithmcited by 13
  14. 2022Prior-Guided One-shot Neural Architecture Searchcited by 12
  15. 2022Arch-Graph: Acyclic Architecture Relation Predictor for Task-Transferable Neural Architecture Searchcited by 9
  16. 2021Cascade Bagging for Accuracy Prediction with Few Training Samplescited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 0; 2025: 1; 2026: 1.

7 papers.

  1. 2023DisWOT: Student Architecture Search for Distillation WithOut Trainingcited by 29
  2. 2023RD-NAS: Enhancing One-shot Supernet Ranking Ability via Ranking Distillation from Zero-cost Proxiescited by 7
  3. 2023Pruning Large Language Models via Accuracy Predictorcited by 5
  4. 2023TVT: Training-Free Vision Transformer Search on Tiny Datasetscited by 3
  5. 2025MiCo: End-to-End Mixed Precision Neural Network Co-Exploration Framework for Edge AIcited by 2
  6. 2023A Survey on Recent Teacher-student Learning Studiescited by 1
  7. 2026MiCoPro: End-to-End Mixed Precision HW/SW Co-design with HW-aware Proxy Modelcited by 0