mlsanityData to 7 Oct 2026

DARTS: Differentiable Architecture Search

arXiv 1806.09055 ↗First posted 24 Jun 2018cs.LG cs.CL cs.CVcited by 1,782

Not on the map. Why?

Cited by 29 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

This paper addresses the scalability challenge of architecture search by formulating the task in a differentiable manner. Unlike conventional approaches of applying evolution or reinforcement learning over a discrete and non-differentiable search space, our method is based on the continuous relaxation of the architecture representation, allowing efficient search of the architecture using gradient descent. Extensive experiments on CIFAR-10, ImageNet, Penn Treebank and WikiText-2 show that our algorithm excels in discovering high-performance convolutional architectures for image classification and recurrent architectures for language modeling, while being orders of magnitude faster than state-of-the-art non-differentiable techniques. Our implementation has been made publicly available to facilitate further research on efficient architecture search algorithms.

Key facts. Cited by 1,782 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 0; 2021: 472; 2022: 370; 2023: 323; 2024: 256; 2025: 199; 2026: 161.

1,782 papers.

Sort:

By area:

  1. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
  2. 2021Domain Generalization: A Surveycited by 760
  3. 2021Carbon Emissions and Large Neural Network Trainingcited by 561
  4. 2023Symbolic Discovery of Optimization Algorithmscited by 423
  5. 2021Dynamic Neural Networks: A Surveycited by 405
  6. 2021A Survey of Transformerscited by 399
  7. 2021Rethinking Spatial Dimensions of Vision Transformerscited by 361
  8. 2021True Few-Shot Learning with Language Modelscited by 343
  9. 2021Transformers Can Do Bayesian Inferencecited by 338
  10. 2022ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Codingcited by 296
  11. 2022Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuningcited by 292
  12. 2022EfficientFormer: Vision Transformers at MobileNet Speedcited by 240
38 more
  1. 2021Coordinate Attention for Efficient Mobile Network Designcited by 239
  2. 2024LocalMamba: Visual State Space Model with Windowed Selective Scancited by 235
  3. 2021Parametric Contrastive Learningcited by 217
  4. 2025AIDE: AI-Driven Exploration in the Space of Codecited by 206
  5. 2023A Survey on Deep Neural Network Pruning-Taxonomy, Comparison, Analysis, and Recommendationscited by 200
  6. 2021Zero-Cost Proxies for Lightweight NAScited by 194
  7. 2021Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspectivecited by 168
  8. 2025Multi-agent Architecture Search via Agentic Supernetcited by 164
  9. 2022A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunitiescited by 162
  10. 2022Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNscited by 155
  11. 2021Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Bettercited by 153
  12. 2021Investigating Bi-Level Optimization for Learning and Vision from a Unified Perspective: A Survey and Beyondcited by 151
  13. 2021Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challengescited by 143
  14. 2023Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Surveycited by 140
  15. 2023Neural Architecture Search: Insights from 1000 Paperscited by 136
  16. 2022Neural Prompt Searchcited by 133
  17. 2021CrypTen: Secure Multi-Party Computation Meets Machine Learningcited by 131
  18. 2023MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devicescited by 120
  19. 2025Multi-Agent Design: Optimizing Agents with Better Prompts and Topologiescited by 106
  20. 2022Condensing Graphs via One-Step Gradient Matchingcited by 100
  21. 2021Involution: Inverting the Inherence of Convolution for Visual Recognitioncited by 99
  22. 2022A framework for bilevel optimization that enables stochastic and global variance reduction algorithmscited by 99
  23. 2021ResLT: Residual Learning for Long-tailed Recognitioncited by 96
  24. 2022Deep Image Deblurring: A Surveycited by 94
  25. 2021Rethinking Architecture Selection in Differentiable NAScited by 92
  26. 2021Parameter Prediction for Unseen Deep Architecturescited by 89
  27. 2021How Powerful are Performance Predictors in Neural Architecture Search?cited by 88
  28. 2021Diverse Branch Block: Building a Convolution as an Inception-like Unitcited by 87
  29. 2021MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learningcited by 87
  30. 2023Data Distillation: A Surveycited by 86
  31. 2023LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimizationcited by 86
  32. 2021HW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmarkcited by 83
  33. 2021Dynamic Slimmable Networkcited by 83
  34. 2022OpenEarthMap: A Benchmark Dataset for Global High-Resolution Land Cover Mappingcited by 80
  35. 2023Full Stack Optimization of Transformer Inference: a Surveycited by 79
  36. 2022Deep Model Reassemblycited by 78
  37. 2023DiffRate : Differentiable Compression Rate for Efficient Vision Transformerscited by 78
  38. 2024AutoFlow: Automated Workflow Generation for Large Language Model Agentscited by 76

50 most cited of 1,782 All 1,782 (JSON)