mlsanityData to 7 Oct 2026

Global optimization of graph acquisition functions for neural architecture search

arXiv 2505.23640 ↗First posted 29 May 2025cs.LG math.OCcited by 2

Not on the map. Why?

Abstract (arXiv)

Graph Bayesian optimization (BO) has shown potential as a powerful and data-efficient tool for neural architecture search (NAS). Most existing graph BO works focus on developing graph surrogates models, i.e., metrics of networks and/or different kernels to quantify the similarity between networks. However, the acquisition optimization, as a discrete optimization task over graph structures, is not well studied due to the complexity of formulating the graph search space and acquisition functions. This paper presents explicit optimization formulations for graph input space including properties such as reachability and shortest paths, which are used later to formulate graph kernels and the acquisition function. We theoretically prove that the proposed encoding is an equivalent representation of the graph space and provide restrictions for the NAS domain with either node or edge labels. Numerical results over several NAS benchmarks show that our method efficiently finds the optimal architecture for most cases, highlighting its efficacy.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 39 of its 56 references that are in the map. First posted on arXiv 29 May 2025.

Builds on

39 of 56 references.

References · 39

  1. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  2. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  3. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 902
  4. 2018A Tutorial on Bayesian Optimizationcited by 734
  5. 2017Progressive Neural Architecture Searchcited by 483
  6. 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 480
  7. 2020NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Searchcited by 412
  8. 2019NAS-Bench-101: Towards Reproducible Neural Architecture Searchcited by 340
  9. 2015Scalable Bayesian Optimization Using Deep Neural Networkscited by 284
  10. 2020A Comprehensive Survey of Neural Architecture Search: Challenges and Solutionscited by 253
  11. 2018Neural Architecture Search with Bayesian Optimisation and Optimal Transportcited by 192
  12. 2019BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Searchcited by 175
27 more
  1. 2019A Survey on Graph Kernelscited by 148
  2. 2016GPflow: A Gaussian process library using TensorFlowcited by 139
  3. 2023Neural Architecture Search: Insights from 1000 Paperscited by 136
  4. 2019Neural Predictor for Neural Architecture Searchcited by 116
  5. 2018Strong mixed-integer programming formulations for trained neural networkscited by 115
  6. 2020Graph Kernels: State-of-the-Art and Future Challengescited by 63
  7. 2018GraKeL: A Graph Kernel Library in Pythoncited by 54
  8. 2016On Valid Optimal Assignment Kernels and Applications to Graph Classificationcited by 49
  9. 2019Graph Kernels: A Surveycited by 43
  10. 2021Partition-based formulations for mixed-integer optimization of trained ReLU neural networkscited by 39
  11. 2023When Deep Learning Meets Polyhedral Theory: A Surveycited by 39
  12. 2020A Study on Encodings for Neural Architecture Searchcited by 37
  13. 2017Optimization of Tree Ensemblescited by 26
  14. 2020Exploring the Loss Landscape in Neural Architecture Searchcited by 20
  15. 2021DPNAS: Neural Architecture Search for Deep Learning with Differential Privacycited by 20
  16. 2022Maximizing information from chemical engineering data sets: Applications to machine learningcited by 17
  17. 2018Mixed-Integer Convex Nonlinear Optimization with Gradient-Boosted Trees Embeddedcited by 16
  18. 2020Global Optimization of Gaussian processescited by 14
  19. 2020ENTMOOT: A Framework for Optimization over Ensemble Tree Modelscited by 13
  20. 2024Verifying message-passing neural networks via topology-based bounds tighteningcited by 10
  21. 2023Mixed-Integer Optimisation of Graph Neural Networks for Computer-Aided Molecular Designcited by 9
  22. 2024Global Optimization of Gaussian Process Acquisition Functions Using a Piecewise-Linear Kernel Approximationcited by 8
  23. 2023Bayesian Optimisation of Functions on Graphscited by 7
  24. 2025BoGrape: Bayesian optimization over graphs with shortest-path encodedcited by 7
  25. 2023Augmenting optimization-based molecular design with graph neural networkscited by 6
  26. 2023Optimizing over trained GNNs via symmetry breakingcited by 5
  27. 2019ProBO: Versatile Bayesian Optimization Using Any Probabilistic Programming Languagecited by 3

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025The Catechol Benchmark: Time-series Solvent Selection Data for Few-shot Machine Learningcited by 3
  2. 2025Global Optimization on Graph-Structured Data via Gaussian Processes with Spectral Representationscited by 0