mlsanityData to 13 Oct 2026

NAS-Bench-1Shot1: Benchmarking and Dissecting One-shot Neural Architecture Search

arXiv 2001.10422 ↗First posted 28 Jan 2020cs.LG cs.CV cs.NEcited by 64

Not on the map. Why?

Abstract (arXiv)

One-shot neural architecture search (NAS) has played a crucial role in making NAS methods computationally feasible in practice. Nevertheless, there is still a lack of understanding on how these weight-sharing algorithms exactly work due to the many factors controlling the dynamics of the process. In order to allow a scientific study of these components, we introduce a general framework for one-shot NAS that can be instantiated to many recently-introduced variants and introduce a general benchmarking framework that draws on the recent large-scale tabular benchmark NAS-Bench-101 for cheap anytime evaluations of one-shot NAS methods. To showcase the framework, we compare several state-of-the-art one-shot NAS methods, examine how sensitive they are to their hyperparameters and how they can be improved by tuning their hyperparameters, and compare their performance to that of blackbox optimizers for NAS-Bench-101.

Key facts. Cited by 64 papers in the map (data through 13 Oct 2026). First posted on arXiv 28 Jan 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2021: 34; 2022: 13; 2023: 11; 2024: 2; 2025: 1; 2026: 3.

64 papers.

Sort:

  1. 2021SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimizationcited by 229
  2. 2023Neural Architecture Search: Insights from 1000 Paperscited by 139
  3. 2021HPOBench: A Collection of Reproducible Multi-Fidelity Benchmark Problems for HPOcited by 111
  4. 2021How Powerful are Performance Predictors in Neural Architecture Search?cited by 88
  5. 2022β-DARTS: Beta-Decay Regularization for Differentiable Architecture Searchcited by 64
  6. 2021BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Searchcited by 63
  7. 2021A Comprehensive Survey on Hardware-Aware Neural Architecture Searchcited by 60
  8. 2022AMLB: an AutoML Benchmarkcited by 55
  9. 2021iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradientscited by 51
  10. 2022Monte Carlo Tree Search based Variable Selection for High Dimensional Bayesian Optimizationcited by 37
  11. 2022NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easycited by 36
  12. 2023Are Random Decompositions all we need in High Dimensional Bayesian Optimisation?cited by 36
38 more
  1. 2021NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse Taskscited by 32
  2. 2021NASI: Label- and Data-agnostic Neural Architecture Search at Initializationcited by 28
  3. 2021Towards Green Automated Machine Learning: Status Quo and Future Directionscited by 25
  4. 2022NAS-Bench-Graph: Benchmarking Graph Neural Architecture Searchcited by 25
  5. 2021EPE-NAS: Efficient Performance Estimation Without Training for Neural Architecture Searchcited by 24
  6. 2021Analyzing and Mitigating Interference in Neural Architecture Searchcited by 20
  7. 2021NAS-Bench-x11 and the Power of Learning Curvescited by 20
  8. 2021Rethinking Neural Operations for Diverse Taskscited by 18
  9. 2021Accelerating Neural Architecture Search via Proxy Datacited by 14
  10. 2021Automated Deep Learning: Neural Architecture Search Is Not the Endcited by 13
  11. 2022EC-NAS: Energy Consumption Aware Tabular Benchmarks for Neural Architecture Searchcited by 11
  12. 2024HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Modelscited by 10
  13. 2021Zero-Cost Operation Scoring in Differentiable Architecture Searchcited by 9
  14. 2021EEEA-Net: An Early Exit Evolutionary Neural Architecture Searchcited by 9
  15. 2021NAS-HPO-Bench-II: A Benchmark Dataset on Joint Optimization of Convolutional Neural Network Architecture and Training Hyperparameterscited by 9
  16. 2024FlowerFormer: Empowering Neural Architecture Encoding using a Flow-aware Graph Transformercited by 9
  17. 2021Neural Architecture Search as Program Transformation Explorationcited by 8
  18. 2021Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture Searchcited by 8
  19. 2021Sandwich Batch Normalization: A Drop-In Replacement for Feature Distribution Heterogeneitycited by 7
  20. 2023β-DARTS++: Bi-level Regularization for Proxy-robust Differentiable Architecture Searchcited by 7
  21. 2022BLOX: Macro Neural Architecture Search Benchmark and Algorithmscited by 6
  22. 2023PA&DA: Jointly Sampling PAth and DAta for Consistent NAScited by 6
  23. 2021Contrastive Self-supervised Neural Architecture Searchcited by 5
  24. 2021BaLeNAS: Differentiable Architecture Search via the Bayesian Learning Rulecited by 5
  25. 2022CLOSE: Curriculum Learning On the Sharing Extent Towards Better One-shot NAScited by 5
  26. 2021Bag of Tricks for Neural Architecture Searchcited by 4
  27. 2021Fitness Landscape Footprint: A Framework to Compare Neural Architecture Search Problemscited by 4
  28. 2022Neural Capacitance: A New Perspective of Neural Network Selection via Edge Dynamicscited by 3
  29. 2023Are Neural Architecture Search Benchmarks Well Designed? A Deeper Look Into Operation Importancecited by 3
  30. 2023Optimizing with Low Budgets: a Comparison on the Black-box Optimization Benchmarking Suite and OpenAI Gymcited by 3
  31. 2025Energy-Aware Deep Learning on Resource-Constrained Hardwarecited by 3
  32. 2021An Analysis of Super-Net Heuristics in Weight-Sharing NAScited by 2
  33. 2021Towards a Robust Differentiable Architecture Search under Label Noisecited by 2
  34. 2021A Data-driven Approach to Neural Architecture Search Initializationcited by 2
  35. 2022Shortest Edit Path Crossover: A Theory-driven Solution to the Permutation Problem in Evolutionary Neural Architecture Searchcited by 2
  36. 2023MO-DEHB: Evolutionary-based Hyperband for Multi-Objective Optimizationcited by 2
  37. 2023Rethink DARTS Search Space and Renovate a New Benchmarkcited by 2
  38. 2023Robustifying DARTS by Eliminating Information Bypass Leakage via Explicit Sparse Regularizationcited by 2

50 most cited of 64 All 64 (JSON)