Abstract
As neural architecture search (NAS) becomes an increasingly adopted method to design network architectures, various methods have been proposed to speedup the process. Besides proxy evaluation tasks, weight sharing, and scaling down the evaluated architectures, performance-predicting models exhibit multiple advantages. Eliminating the need to train candidate architectures and enabling transfer learning between datasets, researchers can also utilize them as a surrogate function for Bayesian optimization. On the other hand, graph convolutional networks (GCNs) have also been increasingly adopted for various tasks, enabling deep learning techniques on graphs without feature engineering. In this paper, we employ an evolutionary-based NAS method to evolve GCNs for the problem of predicting the relative performance of various architectures included in the NAS-Bench-101 dataset. By fine-tuning the architecture generated by our methodology, we manage to achieve a Kendall’s tau correlation coefficient of 0.907 between 1050 completely unseen architectures, utilizing only 450 samples, while also outperforming a strong baseline on the same task. Furthermore, we validate our method on custom global search space architectures, generated for the Fashion-MNIST dataset.
Similar content being viewed by others
References
Cai H, Yang J, Zhang W, Han S, Yu Y (2018) Path-level network transformation for efficient architecture search. arXiv:1806.02639
Chau T, Dudziak Ł, Abdelfattah MS, Lee R, Kim H, Lane ND (2020) Brp-nas: prediction-based nas using gcns. arXiv:2007.08668
Deng B, Yan J, Lin D (2017) Peephole: predicting network performance before training. arXiv:1712.03351
Dong X, Yang Y (2020) Nas-bench-102: Extending the scope of reproducible neural architecture search. arXiv:2001.00326
Gao Y, Yang H, Zhang P, Zhou C, Hu Y (2019) Graphnas: graph neural architecture search with reinforcement learning. arXiv:1904.09981
Hamilton W, Ying Z, Leskovec J (2017) Inductive representation learning on large graphs
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780
Kacprzyk J, Pedrycz W (2015) Springer handbook of computational intelligence. Springer, Berlin
Kandasamy K, Neiswanger W, Schneider J, Poczos B, Xing EP (2018) Neural architecture search with Bayesian optimisation and optimal transport. arXiv:1802.07191
Kendall MG (1938) A new measure of rank correlation. Biometrika 30(1/2):81–93
Kipf TN, Welling M (2016) Semi-supervised classification with graph convolutional networks. arXiv:1609.02907
Krizhevsky A, Hinton G et al. (2009) Learning multiple layers of features from tiny images
Kyriakides G, Margaritis K (2020) The effect of reduced training in neural architecture search. Neural Comput Appl 32(23):17321–17332
LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278–2324
Liu C, Zoph B, Neumann M, Shlens J, Hua W, Li LJ, Fei-Fei L, Yuille A, Huang J, Murphy K (2018) Progressive neural architecture search. http://github.com/tensorflow/
Liu H, Simonyan K, Vinyals O, Fernando C, Kavukcuoglu K (2018) Hierarchical representations for efficient architecture search. In: 6th international conference on learning representations, ICLR 2018—conference track proceedings. arxiv:1711.00436
Long D, Zhang S, Zhang Y (2019) Performance prediction based on neural architecture features. Cogn Comput Syst 2(2):80–83
Loshchilov I, Hutter F (2017) Decoupled weight decay regularization. arXiv:1711.05101
Luo R, Tian F, Qin T, Chen E, Liu TY (2018) Neural architecture optimization. Adv Neural Inf Process Syst 2018:7816–7827
Miikkulainen R, Liang J, Meyerson E, Rawal A, Fink D, Francon O, Raju B, Shahrzad H, Navruzyan A, Duffy N et al (2019) Evolving deep neural networks. In: Artificial intelligence in the age of neural networks and brain computing. Elsevier, pp 293–312
Pham H, Guan MY, Zoph B, Le QV, Dean J (2018) Efficient neural architecture search via parameter sharing. In: 35th international conference on machine learning, ICML 2018, vol 9, pp. 6522–6531. arXiv:1802.03268
Real E, Aggarwal A, Huang Y, Le QV (2019) Regularized evolution for image classifier architecture search. Proc AAAI Conf Artif Intell 33:4780–4789. https://doi.org/10.1609/aaai.v33i01.33014780
Schlichtkrull M, Kipf TN, Bloem P, Van Den Berg R, Titov I, Welling M (2018) Modeling relational data with graph convolutional networks
Smith LN (2017) Cyclical learning rates for training neural networks. In: 2017 IEEE winter conference on applications of computer vision (WACV). IEEE, pp 464–472
Stanley KO, Miikkulainen R (2002) Evolving neural networks through augmenting topologies. Evol Comput 10(2):99–127
Sun Y, Wang H, Xue B, Jin Y, Yen GG, Zhang M (2019) Surrogate-assisted evolutionary deep learning using an end-to-end random forest-based performance predictor. IEEE Trans Evol Comput 24(2):350–364
Tang Y, Wang Y, Xu Y, Chen H, Shi B, Xu C, Xu C, Tian Q, Xu C (2020) A semi-supervised assessor of neural architectures. In: IEEE/CVF conference on computer vision and pattern recognition, pp. 1810–1819
Xiao H, Rasul K, Vollgraf R (2017) Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. arXiv:1708.07747
Xu Y, Wang Y, Han K, Jui S, Xu C, Tian Q, Xu C (2019) Renas: relativistic evaluation of neural architecture search. arXiv:1910.01523
Ying C, Klein A, Real E, Christiansen E, Murphy K, Hutter F (2019) Nas-bench-101: towards reproducible neural architecture search. arXiv:1902.09635
Zela A, Siems J, Hutter F (2020) Nas-bench-1shot1: benchmarking and dissecting one-shot neural architecture search. arXiv:2001.10422
Zhao H, Wei L, Yao Q (2020) Simplifying architecture search for graph neural network. arXiv:2008.11652
Zhong Z, Yan J, Wu W, Shao J, Liu CL (2018) Practical block-wise neural network architecture generation. In: IEEE conference on computer vision and pattern recognition, pp. 2423–2432
Zhou K, Song Q, Huang X, Hu X (2019) Auto-gnn: neural architecture search of graph neural networks. arXiv:1909.03184
Zoph B, Le QV (2016) Neural architecture search with reinforcement learning. arXiv:1611.01578
Zoph B, Vasudevan V, Shlens J, Le QV (2018) Learning transferable architectures for scalable image recognition. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition, pp 8697–8710. arXiv:1707.07012
Acknowledgements
This work was supported by computational time granted from the Greek Research & Technology Network (GRNET) in the National HPC facility—ARIS—under Project ID ECN, which enabled the development of the method. The research work was supported by the Hellenic Foundation for Research and Innovation (HFRI) under the HFRI Ph.D. Fellowship Grant (Fellowship Number: 646).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Funded by the Hellenic Foundation for Research and Innovation (HFRI) under the HFRI PhD Fellowship Grant (Fellowship Number: 646).
Rights and permissions
About this article
Cite this article
Kyriakides, G., Margaritis, K. Evolving graph convolutional networks for neural architecture search. Neural Comput & Applic 34, 899–909 (2022). https://doi.org/10.1007/s00521-021-05979-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-021-05979-8