mlsanityData to 14 Oct 2026

When NAS Meets Trees: An Efficient Algorithm for Neural Architecture Search

arXiv 2204.04918 ↗First posted 11 Apr 2022cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

The key challenge in neural architecture search (NAS) is designing how to explore wisely in the huge search space. We propose a new NAS method called TNAS (NAS with trees), which improves search efficiency by exploring only a small number of architectures while also achieving a higher search accuracy. TNAS introduces an architecture tree and a binary operation tree, to factorize the search space and substantially reduce the exploration size. TNAS performs a modified bi-level Breadth-First Search in the proposed trees to discover a high-performance architecture. Impressively, TNAS finds the global optimal architecture on CIFAR-10 with test accuracy of 94.37% in four GPU hours in NAS-Bench-201. The average test accuracy is 94.35%, which outperforms the state-of-the-art. Code is available at: urlhttps://github.com/guochengqian/TNAS.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 39 of its 45 references that are in the map. First posted on arXiv 11 Apr 2022.

Builds on

39 of 45 references.

References · 39

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  3. 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
  4. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,101
  5. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 909
  6. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 837
  7. 2017Progressive Neural Architecture Searchcited by 487
  8. 2020NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Searchcited by 416
  9. 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 414
  10. 2017Large-Scale Evolution of Image Classifierscited by 348
  11. 2019NAS-Bench-101: Towards Reproducible Neural Architecture Searchcited by 344
  12. 2016Designing Neural Network Architectures using Reinforcement Learningcited by 279
27 more
  1. 2019Searching for A Robust Neural Architecture in Four GPU Hourscited by 260
  2. 2019Random Search and Reproducibility for Neural Architecture Searchcited by 254
  3. 2020Neural Architecture Search without Trainingcited by 244
  4. 2019Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluationcited by 230
  5. 2017SMASH: One-Shot Model Architecture Search through HyperNetworkscited by 202
  6. 2021Zero-Cost Proxies for Lightweight NAScited by 199
  7. 2020BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Modelscited by 188
  8. 2021Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspectivecited by 169
  9. 2020FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensionscited by 152
  10. 2019Evaluating the Search Phase of Neural Architecture Searchcited by 120
  11. 2019Blockwisely Supervised Neural Architecture Search with Knowledge Distillationcited by 81
  12. 2020DARTS-: Robustly Stepping out of Performance Collapse Without Indicatorscited by 81
  13. 2018ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptationcited by 76
  14. 2019SGAS: Sequential Greedy Architecture Searchcited by 69
  15. 2020GreedyNAS: Towards Fast One-Shot NAS with Greedy Supernetcited by 69
  16. 2020Can weight sharing outperform random architecture search? An investigation with TuNAScited by 68
  17. 2021BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Searchcited by 63
  18. 2020Few-shot Neural Architecture Searchcited by 50
  19. 2020Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Searchcited by 38
  20. 2021Neural Architecture Search with Random Labelscited by 33
  21. 2020Angle-based Search Space Shrinking for Neural Architecture Searchcited by 32
  22. 2018BlockQNN: Efficient Block-wise Neural Network Architecture Generationcited by 31
  23. 2021Stronger NAS with Weaker Predictorscited by 28
  24. 2020DOTS: Decoupling Operation and Topology in Differentiable Architecture Searchcited by 23
  25. 2021K-shot NAS: Learnable Weight-Sharing for NAS with K-shot Supernetscited by 22
  26. 2021BN-NAS: Neural Architecture Search with Batch Normalizationcited by 21
  27. 2020Rethinking Performance Estimation in Neural Architecture Searchcited by 7

Built on by

Cited by year

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

3 papers.

  1. 2024OStr-DARTS: Differentiable Neural Architecture Search based on Operation Strengthcited by 4
  2. 2023Balanced Mixture of SuperNets for Learning the CNN Pooling Architecturecited by 1
  3. 2025Neural Architecture Search by Learning a Hierarchical Search Spacecited by 0