mlsanityData to 14 Oct 2026

BLOX: Macro Neural Architecture Search Benchmark and Algorithms

arXiv 2210.07271 ↗First posted 13 Oct 2022cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Neural architecture search (NAS) has been successfully used to design numerous high-performance neural networks. However, NAS is typically compute-intensive, so most existing approaches restrict the search to decide the operations and topological structure of a single block only, then the same block is stacked repeatedly to form an end-to-end model. Although such an approach reduces the size of search space, recent studies show that a macro search space, which allows blocks in a model to be different, can lead to better performance. To provide a systematic study of the performance of NAS algorithms on a macro search space, we release Blox - a benchmark that consists of 91k unique models trained on the CIFAR-100 dataset. The dataset also includes runtime measurements of all the models on a diverse set of hardware platforms. We perform extensive experiments to compare existing algorithms that are well studied on cell-based search spaces, with the emerging blockwise approaches that aim to make NAS scalable to much larger macro search spaces. The benchmark and code are available at https://github.com/SamsungLabs/blox.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 35 of its 59 references that are in the map. First posted on arXiv 13 Oct 2022.

Builds on

35 of 59 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  6. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  7. 2017Squeeze-and-Excitation Networkscited by 4,789
  8. 2014Going Deeper with Convolutionscited by 4,241
  9. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  10. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  11. 2019Searching for MobileNetV3cited by 1,994
  12. 2018DARTS: Differentiable Architecture Searchcited by 1,798
23 more
  1. 2016Neural Architecture Search with Reinforcement Learningcited by 1,499
  2. 2018Datasheets for Datasetscited by 1,386
  3. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,135
  4. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,101
  5. 2016An overview of gradient descent optimization algorithmscited by 1,033
  6. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 943
  7. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 909
  8. 2016Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimizationcited by 699
  9. 2020NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Searchcited by 416
  10. 2019NAS-Bench-101: Towards Reproducible Neural Architecture Searchcited by 344
  11. 2016Designing Neural Network Architectures using Reinforcement Learningcited by 279
  12. 2021Zero-Cost Proxies for Lightweight NAScited by 199
  13. 2019BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Searchcited by 179
  14. 2018Neural Architecture Optimizationcited by 167
  15. 2020BRP-NAS: Prediction-based NAS using GCNscited by 111
  16. 2021Rethinking Architecture Selection in Differentiable NAScited by 92
  17. 2019Blockwisely Supervised Neural Architecture Search with Knowledge Distillationcited by 81
  18. 2020NAS-Bench-1Shot1: Benchmarking and Dissecting One-shot Neural Architecture Searchcited by 64
  19. 2020NAS-Bench-NLP: Neural Architecture Search Benchmark for Natural Language Processingcited by 60
  20. 2020Distilling Optimal Neural Networks: Rapid Search in Diverse Spacescited by 32
  21. 2021Prioritized Architecture Sampling with Monto-Carlo Tree Searchcited by 32
  22. 2021LANA: Latency Aware Network Accelerationcited by 11
  23. 2020NPENAS: Neural Predictor Guided Evolution for Neural Architecture Searchcited by 3

Built on by

Cited by year

Citing papers per year: 2023: 5; 2024: 1.

6 papers.

  1. 2024Encodings for Prediction-based Neural Architecture Searchcited by 9
  2. 2023MathNAS: If Blocks Have a Role in Mathematical Architecture Designcited by 4
  3. 2023Are Neural Architecture Search Benchmarks Well Designed? A Deeper Look Into Operation Importancecited by 3
  4. 2023How Much Is Hidden in the NAS Benchmarks? Few-Shot Adaptation of a NAS Predictorcited by 2
  5. 2023Balanced Mixture of SuperNets for Learning the CNN Pooling Architecturecited by 1
  6. 2023DONNAv2 -- Lightweight Neural Architecture Search for Vision taskscited by 0