mlsanityData to 7 Oct 2026

Large-Scale Evolution of Image Classifiers

arXiv 1703.01041 ↗First posted 3 Mar 2017cs.NE cs.AI cs.CVcited by 348

Not on the map. Why?

Abstract (arXiv)

Neural networks have proven effective at solving difficult problems but designing their architectures can be challenging, even for image classification problems alone. Our goal is to minimize human participation, so we employ evolutionary algorithms to discover such networks automatically. Despite significant computational requirements, we show that it is now possible to evolve models with accuracies within the range of those published in the last year. Specifically, we employ simple evolutionary techniques at unprecedented scales to discover models for the CIFAR-10 and CIFAR-100 datasets, starting from trivial initial conditions and reaching accuracies of 94.6% (95.6% for ensemble) and 77.0%, respectively. To do this, we use novel and intuitive mutation operators that navigate large search spaces; we stress that no human participation is required once evolution starts and that the output is a fully-trained model. Throughout this work, we place special emphasis on the repeatability of results, the variability in the outcomes and the computational requirements.

Key facts. Cited by 348 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Mar 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 106; 2022: 90; 2023: 60; 2024: 52; 2025: 27; 2026: 12.

348 papers.

Sort:

By area:

  1. 2021Primer: Searching for Efficient Transformers for Language Modelingcited by 162
  2. 2021Embodied Intelligence via Learning and Evolutioncited by 154
  3. 2022Multiview Transformers for Video Recognitioncited by 148
  4. 2023Neural Architecture Search: Insights from 1000 Paperscited by 136
  5. 2022Neural Prompt Searchcited by 133
  6. 2023EvoPrompting: Language Models for Code-Level Neural Architecture Searchcited by 129
  7. 2023Structured Pruning for Deep Convolutional Neural Networks: A surveycited by 122
  8. 2021Rethinking Architecture Selection in Differentiable NAScited by 92
  9. 2022Deep Model Reassemblycited by 78
  10. 2023Can GPT-4 Perform Neural Architecture Search?cited by 74
  11. 2021Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learningcited by 72
  12. 2021Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognitioncited by 71
38 more
  1. 2021Exploring Relational Context for Multi-Task Dense Predictioncited by 71
  2. 2022GradMax: Growing Neural Networks using Gradient Informationcited by 64
  3. 2021A Comprehensive Survey on Hardware-Aware Neural Architecture Searchcited by 60
  4. 2023ZiCo: Zero-shot NAS via Inverse Coefficient of Variation on Gradientscited by 57
  5. 2021Evolving Reinforcement Learning Algorithmscited by 48
  6. 2020Towards Crowdsourced Training of Large Neural Networks using Decentralized Mixture-of-Expertscited by 43
  7. 2022AutoSNN: Towards Energy-Efficient Spiking Neural Networkscited by 40
  8. 2021The future of human-AI collaboration: a taxonomy of design knowledge for hybrid intelligence systemscited by 39
  9. 2021HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformerscited by 39
  10. 2021Automated Machine Learning on Graphs: A Surveycited by 38
  11. 2024Lightweight Deep Learning for Resource-Constrained Environments: A Surveycited by 38
  12. 2021Teachers Do More Than Teach: Compressing Image-to-Image Modelscited by 37
  13. 2021Pooling Architecture Search for Graph Classificationcited by 36
  14. 2021AutoDropout: Learning Dropout Patterns to Regularize Deep Networkscited by 35
  15. 2021AdvRush: Searching for Adversarially Robust Neural Architecturescited by 28
  16. 2021Towards Improving the Consistency, Efficiency, and Flexibility of Differentiable Neural Architecture Searchcited by 27
  17. 2021Rethinking Graph Neural Architecture Search from Message-passingcited by 26
  18. 2022NAS-Bench-Graph: Benchmarking Graph Neural Architecture Searchcited by 25
  19. 2021Core-set Sampling for Efficient Neural Architecture Searchcited by 23
  20. 2021CATE: Computation-aware Neural Architecture Encoding with Transformerscited by 21
  21. 2023Zero-Shot Neural Architecture Search: Challenges, Solutions, and Opportunitiescited by 21
  22. 2021Analyzing and Mitigating Interference in Neural Architecture Searchcited by 20
  23. 2021DPNAS: Neural Architecture Search for Deep Learning with Differential Privacycited by 20
  24. 2021PyGlove: Symbolic Programming for Automated Machine Learningcited by 19
  25. 2021Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimizationcited by 19
  26. 2021Designing the Topology of Graph Neural Networks: A Novel Feature Fusion Perspectivecited by 19
  27. 2022Demystifying the Neural Tangent Kernel from a Practical Perspective: Can it be trusted for Neural Architecture Search without training?cited by 18
  28. 2022Neural Architecture Search as Multiobjective Optimization Benchmarks: Problem Formulation and Performance Assessmentcited by 17
  29. 2024Puzzle: Distillation-Based NAS for Inference-Optimized LLMscited by 17
  30. 2022Winning solutions and post-challenge analyses of the ChaLearn AutoDL challenge 2019cited by 16
  31. 2022Pruning Networks with Cross-Layer Ranking & k-Reciprocal Nearest Filterscited by 16
  32. 2024SLED: Self Logits Evolution Decoding for Improving Factuality in Large Language Modelscited by 16
  33. 2021Trilevel Neural Architecture Search for Efficient Single Image Super-Resolutioncited by 15
  34. 2021Derivative-Free Reinforcement Learning: A Reviewcited by 15
  35. 2021FBNetV5: Neural Architecture Search for Multiple Tasks in One Runcited by 15
  36. 2022Learning Where To Look -- Generative NAS is Surprisingly Efficientcited by 15
  37. 2022Lambda-DARTS: Mitigating Performance Collapse by Harmonizing Operation Selection among Cellscited by 15
  38. 2023Lightweight Neural Architecture Search for Temporal Convolutional Networks at the Edgecited by 15

50 most cited of 348 All 348 (JSON)