mlsanityData to 14 Oct 2026

Graph is all you need? Lightweight data-agnostic neural architecture search without training

arXiv 2405.01306 ↗First posted 2 May 2024cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Neural architecture search (NAS) enables the automatic design of neural network models. However, training the candidates generated by the search algorithm for performance evaluation incurs considerable computational overhead. Our method, dubbed nasgraph, remarkably reduces the computational costs by converting neural architectures to graphs and using the average degree, a graph measure, as the proxy in lieu of the evaluation metric. Our training-free NAS method is data-agnostic and light-weight. It can find the best architecture among 200 randomly sampled architectures from NAS-Bench201 in 217 CPU seconds. Besides, our method is able to achieve competitive performance on various datasets including NASBench-101, NASBench-201, and NDS search spaces. We also demonstrate that nasgraph generalizes to more challenging tasks on Micro TransNAS-Bench-101.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 37 of its 56 references that are in the map. First posted on arXiv 2 May 2024.

Builds on

37 of 56 references.

References · 37

  1. 2022A ConvNet for the 2020scited by 3,579
  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. 2018SNIP: Single-shot Network Pruning based on Connection Sensitivitycited by 812
  8. 2018Gradient Descent Provably Optimizes Over-parameterized Neural Networkscited by 659
  9. 2018Taskonomy: Disentangling Task Transfer Learningcited by 634
  10. 2017Progressive Neural Architecture Searchcited by 487
  11. 2020Pruning neural networks without any data by iteratively conserving synaptic flowcited by 479
  12. 2020Picking Winning Tickets Before Training by Preserving Gradient Flowcited by 471
25 more
  1. 2020NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Searchcited by 416
  2. 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 414
  3. 2017A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasetscited by 377
  4. 2019NAS-Bench-101: Towards Reproducible Neural Architecture Searchcited by 344
  5. 2019PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Searchcited by 265
  6. 2019Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentationcited by 260
  7. 2020Neural Architecture Search without Trainingcited by 244
  8. 2021Zero-Cost Proxies for Lightweight NAScited by 199
  9. 2019BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Searchcited by 179
  10. 2019Understanding and Robustifying Differentiable Architecture Searchcited by 178
  11. 2021Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspectivecited by 169
  12. 2019Complexity of Linear Regions in Deep Networkscited by 167
  13. 2019FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Searchcited by 130
  14. 2019Evaluating the Search Phase of Neural Architecture Searchcited by 120
  15. 2018Faster gaze prediction with dense networks and Fisher pruningcited by 94
  16. 2021Rethinking Architecture Selection in Differentiable NAScited by 92
  17. 2019DetNAS: Backbone Search for Object Detectioncited by 81
  18. 2019On Network Design Spaces for Visual Recognitioncited by 68
  19. 2020EcoNAS: Finding Proxies for Economical Neural Architecture Searchcited by 61
  20. 2021TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Searchcited by 58
  21. 2023ZiCo: Zero-shot NAS via Inverse Coefficient of Variation on Gradientscited by 58
  22. 2022NAS-Bench-Suite-Zero: Accelerating Research on Zero Cost Proxiescited by 36
  23. 2019ASAP: Architecture Search, Anneal and Prunecited by 29
  24. 2020Pruning via Iterative Ranking of Sensitivity Statisticscited by 26
  25. 2013Decompositions of Triangle-Dense Graphscited by 2

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025L-SWAG: Layer-Sample Wise Activation with Gradients information for Zero-Shot NAS on Vision Transformerscited by 5