mlsanityData to 7 Oct 2026

NAS-Bench-101: Towards Reproducible Neural Architecture Search

arXiv 1902.09635 ↗First posted 25 Feb 2019cs.LG stat.MLcited by 340

Not on the map. Why?

Abstract (arXiv)

Recent advances in neural architecture search (NAS) demand tremendous computational resources, which makes it difficult to reproduce experiments and imposes a barrier-to-entry to researchers without access to large-scale computation. We aim to ameliorate these problems by introducing NAS-Bench-101, the first public architecture dataset for NAS research. To build NAS-Bench-101, we carefully constructed a compact, yet expressive, search space, exploiting graph isomorphisms to identify 423k unique convolutional architectures. We trained and evaluated all of these architectures multiple times on CIFAR-10 and compiled the results into a large dataset of over 5 million trained models. This allows researchers to evaluate the quality of a diverse range of models in milliseconds by querying the pre-computed dataset. We demonstrate its utility by analyzing the dataset as a whole and by benchmarking a range of architecture optimization algorithms.

Key facts. Cited by 340 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Feb 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 79; 2022: 73; 2023: 57; 2024: 57; 2025: 46; 2026: 28.

340 papers.

Sort:

By area:

  1. 2023Symbolic Discovery of Optimization Algorithmscited by 423
  2. 2021Dataset Condensation with Distribution Matchingcited by 362
  3. 2021Zero-Cost Proxies for Lightweight NAScited by 194
  4. 2021The Values Encoded in Machine Learning Researchcited by 172
  5. 2023Neural Architecture Search: Insights from 1000 Paperscited by 136
  6. 2021HPOBench: A Collection of Reproducible Multi-Fidelity Benchmark Problems for HPOcited by 111
  7. 2021Generalized Shape Metrics on Neural Representationscited by 109
  8. 2023When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunitiescited by 89
  9. 2021How Powerful are Performance Predictors in Neural Architecture Search?cited by 88
  10. 2023LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimizationcited by 86
  11. 2022Learning to Learn with Generative Models of Neural Network Checkpointscited by 85
  12. 2021HW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmarkcited by 83
38 more
  1. 2021HPO-B: A Large-Scale Reproducible Benchmark for Black-Box HPO based on OpenMLcited by 75
  2. 2021Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognitioncited by 71
  3. 2022DC-BENCH: Dataset Condensation Benchmarkcited by 67
  4. 2021BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Searchcited by 63
  5. 2021YAHPO Gym -- An Efficient Multi-Objective Multi-Fidelity Benchmark for Hyperparameter Optimizationcited by 61
  6. 2021A Comprehensive Survey on Hardware-Aware Neural Architecture Searchcited by 60
  7. 2021TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Searchcited by 57
  8. 2023ZiCo: Zero-shot NAS via Inverse Coefficient of Variation on Gradientscited by 57
  9. 2023CktGNN: Circuit Graph Neural Network for Electronic Design Automationcited by 55
  10. 2022Neural Architecture Search for Spiking Neural Networkscited by 52
  11. 2021iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradientscited by 51
  12. 2023M3D: Dataset Condensation by Minimizing Maximum Mean Discrepancycited by 49
  13. 2021An Evaluation of Edge TPU Accelerators for Convolutional Neural Networkscited by 39
  14. 2021Automated Machine Learning on Graphs: A Surveycited by 38
  15. 2021MQBench: Towards Reproducible and Deployable Model Quantization Benchmarkcited by 38
  16. 2022Model Zoos: A Dataset of Diverse Populations of Neural Network Modelscited by 38
  17. 2022Monte Carlo Tree Search based Variable Selection for High Dimensional Bayesian Optimizationcited by 37
  18. 2022NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easycited by 36
  19. 2022NAS-Bench-Suite-Zero: Accelerating Research on Zero Cost Proxiescited by 36
  20. 2021AutoDropout: Learning Dropout Patterns to Regularize Deep Networkscited by 35
  21. 2023A Survey of Techniques for Optimizing Transformer Inferencecited by 35
  22. 2023AutoML in the Age of Large Language Models: Current Challenges, Future Opportunities and Riskscited by 34
  23. 2021Contrastive Neural Architecture Search with Neural Architecture Comparatorscited by 33
  24. 2021Rapid Neural Architecture Search by Learning to Generate Graphs from Datasetscited by 33
  25. 2021KNAS: Green Neural Architecture Searchcited by 33
  26. 2021NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse Taskscited by 32
  27. 2023TabRepo: A Large Scale Repository of Tabular Model Evaluations and its AutoML Applicationscited by 32
  28. 2021Stronger NAS with Weaker Predictorscited by 28
  29. 2021DACBench: A Benchmark Library for Dynamic Algorithm Configurationcited by 28
  30. 2023Artificial intelligence to advance Earth observation: : A review of models, recent trends, and pathways forwardcited by 28
  31. 2021Towards Green Automated Machine Learning: Status Quo and Future Directionscited by 25
  32. 2022NAS-Bench-Graph: Benchmarking Graph Neural Architecture Searchcited by 25
  33. 2024AZ-NAS: Assembling Zero-Cost Proxies for Network Architecture Searchcited by 25
  34. 2021EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Searchcited by 24
  35. 2021CATE: Computation-aware Neural Architecture Encoding with Transformerscited by 21
  36. 2023Zero-Shot Neural Architecture Search: Challenges, Solutions, and Opportunitiescited by 21
  37. 2024Position: Leverage Foundational Models for Black-Box Optimizationcited by 21
  38. 2021ProxyBO: Accelerating Neural Architecture Search via Bayesian Optimization with Zero-cost Proxiescited by 20

50 most cited of 340 All 340 (JSON)