mlsanityData to 14 Oct 2026

Rethink DARTS Search Space and Renovate a New Benchmark

arXiv 2306.06852 ↗First posted 12 Jun 2023cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

DARTS search space (DSS) has become a canonical benchmark for NAS whereas some emerging works pointed out the issue of narrow accuracy range and claimed it would hurt the method ranking. We observe some recent studies already suffer from this issue that overshadows the meaning of scores. In this work, we first propose and orchestrate a suite of improvements to frame a larger and harder DSS, termed LHD, while retaining high efficiency in search. We step forward to renovate a LHD-based new benchmark, taking care of both discernibility and accessibility. Specifically, we re-implement twelve baselines and evaluate them across twelve conditions by combining two underexpolored influential factors: transductive robustness and discretization policy, to reasonably construct a benchmark upon multi-condition evaluation. Considering that the tabular benchmarks are always insufficient to adequately evaluate the methods of neural architecture search (NAS), our work can serve as a crucial basis for the future progress of NAS. https://github.com/chaoji90/LHD

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 56 of its 73 references that are in the map. First posted on arXiv 12 Jun 2023.

Builds on

56 of 73 references.

References · 56

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Densely Connected Convolutional Networkscited by 6,720
  3. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  4. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  5. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  6. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,101
  7. 2020NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Searchcited by 416
  8. 2019AutoML: A Survey of the State-of-the-Artcited by 390
  9. 2019NAS-Bench-101: Towards Reproducible Neural Architecture Searchcited by 344
  10. 2019PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Searchcited by 265
  11. 2019Searching for A Robust Neural Architecture in Four GPU Hourscited by 260
  12. 2019Random Search and Reproducibility for Neural Architecture Searchcited by 254
38 more
  1. 2020A Comprehensive Survey of Neural Architecture Search: Challenges and Solutionscited by 254
  2. 2018A System for Massively Parallel Hyperparameter Tuningcited by 202
  3. 2022Patches Are All You Need?cited by 201
  4. 2020BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Modelscited by 188
  5. 2019Understanding and Robustifying Differentiable Architecture Searchcited by 178
  6. 2019What Do Compressed Deep Neural Networks Forget?cited by 171
  7. 2020AutoML-Zero: Evolving Machine Learning Algorithms From Scratchcited by 143
  8. 2019Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Searchcited by 131
  9. 2019Evaluating the Search Phase of Neural Architecture Searchcited by 120
  10. 2019Exploring Randomly Wired Neural Networks for Image Recognitioncited by 103
  11. 2022Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling?cited by 103
  12. 2020Stabilizing Differentiable Architecture Search via Perturbation-based Regularizationcited by 102
  13. 2021Rethinking Architecture Selection in Differentiable NAScited by 92
  14. 2021Parameter Prediction for Unseen Deep Architecturescited by 89
  15. 2019Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hourscited by 87
  16. 2020DARTS-: Robustly Stepping out of Performance Collapse Without Indicatorscited by 81
  17. 2020DrNAS: Dirichlet Neural Architecture Searchcited by 73
  18. 2019NAS evaluation is frustratingly hardcited by 70
  19. 2019On Network Design Spaces for Visual Recognitioncited by 68
  20. 2020AttentiveNAS: Improving Neural Architecture Search via Attentive Samplingcited by 66
  21. 2020NAS-Bench-1Shot1: Benchmarking and Dissecting One-shot Neural Architecture Searchcited by 64
  22. 2022β-DARTS: Beta-Decay Regularization for Differentiable Architecture Searchcited by 64
  23. 2021TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Searchcited by 58
  24. 2020MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulationcited by 57
  25. 2019Discovering Neural Wiringscited by 56
  26. 2020Evaluating Efficient Performance Estimators of Neural Architecturescited by 55
  27. 2019Best Practices for Scientific Research on Neural Architecture Searchcited by 54
  28. 2019Understanding Architectures Learnt by Cell-based Neural Architecture Searchcited by 48
  29. 2021Searching the Search Space of Vision Transformercited by 41
  30. 2020Geometry-Aware Gradient Algorithms for Neural Architecture Searchcited by 40
  31. 2020Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Searchcited by 38
  32. 2022NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easycited by 36
  33. 2021Rapid Neural Architecture Search by Learning to Generate Graphs from Datasetscited by 33
  34. 2020Deeper Insights into Weight Sharing in Neural Architecture Searchcited by 24
  35. 2020Towards NNGP-guided Neural Architecture Searchcited by 24
  36. 2018Neural Architecture Search using Deep Neural Networks and Monte Carlo Tree Searchcited by 18
  37. 2022Efficient Architecture Search for Diverse Taskscited by 18
  38. 2021Searching by Generating: Flexible and Efficient One-Shot NAS with Architecture Generatorcited by 15

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025Architecture-Aware Minimization (A2M): How to Find Flat Minima in Neural Architecture Searchcited by 2
  2. 2025confopt: A Library for Implementation and Evaluation of Gradient-based One-Shot NAS Methodscited by 0