mlsanityData to 7 Oct 2026

Do Not Train It: A Linear Neural Architecture Search of Graph Neural Networks

arXiv 2305.14065 ↗First posted 23 May 2023cs.LG cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Neural architecture search (NAS) for Graph neural networks (GNNs), called NAS-GNNs, has achieved significant performance over manually designed GNN architectures. However, these methods inherit issues from the conventional NAS methods, such as high computational cost and optimization difficulty. More importantly, previous NAS methods have ignored the uniqueness of GNNs, where GNNs possess expressive power without training. With the randomly-initialized weights, we can then seek the optimal architecture parameters via the sparse coding objective and derive a novel NAS-GNNs method, namely neural architecture coding (NAC). Consequently, our NAC holds a no-update scheme on GNNs and can efficiently compute in linear time. Empirical evaluations on multiple GNN benchmark datasets demonstrate that our approach leads to state-of-the-art performance, which is up to 200× faster and 18.8% more accurate than the strong baselines.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 42 of its 65 references that are in the map. First posted on arXiv 23 May 2023.

Builds on

42 of 65 references.

References · 42

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2018How Powerful are Graph Neural Networks?cited by 4,355
  6. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,906
  7. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  8. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  9. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  10. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  11. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  12. 2019Simplifying Graph Convolutional Networkscited by 1,470
30 more
  1. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  2. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 875
  3. 2015Image-based Recommendations on Styles and Substitutescited by 702
  4. 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 480
  5. 2019Single Path One-Shot Neural Architecture Search with Uniform Samplingcited by 411
  6. 2018Implicit Bias of Gradient Descent on Linear Convolutional Networkscited by 251
  7. 2020Design Space for Graph Neural Networkscited by 182
  8. 2019Understanding and Robustifying Differentiable Architecture Searchcited by 176
  9. 2021Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspectivecited by 168
  10. 2018Neural Architecture Optimizationcited by 164
  11. 2017Genetic CNNcited by 124
  12. 2020Hyper-Parameter Optimization: A Review of Algorithms and Applicationscited by 114
  13. 2019DARTS+: Improved Differentiable Architecture Search with Early Stoppingcited by 105
  14. 2020Stabilizing Differentiable Architecture Search via Perturbation-based Regularizationcited by 102
  15. 2019Auto-GNN: Neural Architecture Search of Graph Neural Networkscited by 73
  16. 2018GeniePath: Graph Neural Networks with Adaptive Receptive Pathscited by 66
  17. 2016A survey of sparse representation: algorithms and applicationscited by 58
  18. 2020Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gapcited by 50
  19. 2021Search to aggregate neighborhood for graph neural networkcited by 48
  20. 2021Automated Machine Learning on Graphs: A Surveycited by 38
  21. 2015Simple, Efficient, and Neural Algorithms for Sparse Codingcited by 37
  22. 2021NASI: Label- and Data-agnostic Neural Architecture Search at Initializationcited by 28
  23. 2022NAS-Bench-Graph: Benchmarking Graph Neural Architecture Searchcited by 25
  24. 2018You Only Search Once: Single Shot Neural Architecture Search via Direct Sparse Optimizationcited by 23
  25. 2021K-shot NAS: Learnable Weight-Sharing for NAS with K-shot Supernetscited by 22
  26. 2020Probabilistic Dual Network Architecture Search on Graphscited by 15
  27. 2020GOLD-NAS: Gradual, One-Level, Differentiablecited by 15
  28. 2019Stabilizing DARTS with Amended Gradient Estimation on Architectural Parameterscited by 11
  29. 2020Powering One-shot Topological NAS with Stabilized Share-parameter Proxycited by 10
  30. 2021An Alternate Policy Gradient Estimator for Softmax Policiescited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 1; 2025: 1; 2026: 1.

5 papers.

  1. 2023ADGym: Design Choices for Deep Anomaly Detectioncited by 11
  2. 2025ClimateLLM: Efficient Weather Forecasting via Frequency-Aware Large Language Modelscited by 9
  3. 2026No Need to Train Your RDB Foundation Modelcited by 8
  4. 2024GSTAM: Efficient Graph Distillation with Structural Attention-Matchingcited by 1
  5. 2023Explainable Graph Neural Architecture Search via Monte-Carlo Tree Search (Full version)cited by 0