Abstract
Evolutionary algorithms have been widely used in neural architecture search (NAS) in recent years due to their flexible frameworks and promising performance. However, we noticed a lack of attention to algorithm selection, and single-objective algorithms were preferred despite the multiobjective nature of NAS, among prior arts. To explore the reasons behind this preference, we tested mainstream evolutionary algorithms on several standard NAS benchmarks, comparing single and multi-objective algorithms. Additionally, we validated whether the latest evolutionary multi-objective optimization (EMO) algorithms lead to improvement in NAS problems compared to classical EMO algorithms. Our experimental results provide empirical answers to these questions and guidance for the future development of evolutionary NAS algorithms.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bader, J., Zitzler, E.: HypE: an algorithm for fast hypervolume-based many-objective optimization. Evol. Comput. 19(1), 45–76 (2011). https://doi.org/10.1162/EVCO_a_00009
Blank, J., Deb, K., Dhebar, Y., Bandaru, S., Seada, H.: Generating well-spaced points on a unit simplex for evolutionary many-objective optimization. IEEE Trans. Evol. Comput. 25(1), 48–60 (2021). https://doi.org/10.1109/TEVC.2020.2992387
Brown, T.B., et al.: Language models are few-shot learners. CoRR abs/2005.14165 (2020). https://arxiv.org/abs/2005.14165
Cantú, V.H., Azzaro-Pantel, C., Ponsich, A.: Multi-objective evolutionary algorithm based on decomposition (MOEA/D) for optimal design of hydrogen supply chains. In: Pierucci, S., Manenti, F., Bozzano, G.L., Manca, D. (eds.) 30th European Symposium on Computer Aided Process Engineering, Computer Aided Chemical Engineering, vol. 48, pp. 883–888. Elsevier (2020). https://doi.org/10.1016/B978-0-12-823377-1.50148-8,https://www.sciencedirect.com/science/article/pii/B9780128233771501488
Cheng, R., Jin, Y., Olhofer, M., Sendhoff, B.: A reference vector guided evolutionary algorithm for many-objective optimization. IEEE Trans. Evol. Comput. 20(5), 773–791 (2016). https://doi.org/10.1109/TEVC.2016.2519378
Coello Coello, C.A., Reyes Sierra, M.: A study of the parallelization of a coevolutionary multi-objective evolutionary algorithm. In: Monroy, R., Arroyo-Figueroa, G., Sucar, L.E., Sossa, H. (eds.) MICAI 2004. LNCS (LNAI), vol. 2972, pp. 688–697. Springer, Heidelberg (2004). https://doi.org/10.1007/978-3-540-24694-7_71
Deb, K., Pratap, A., Agarwal, S., Meyarivan, T.: A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans. Evol. Comput. 6(2), 182–197 (2002). https://doi.org/10.1109/4235.996017
Deb, K., Jain, H.: An evolutionary many-objective optimization algorithm using reference-point-based nondominated sorting approach, part i: Solving problems with box constraints. IEEE Trans. Evol. Comput. 18(4), 577–601 (2014). https://doi.org/10.1109/TEVC.2013.2281535
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding (2018). https://doi.org/10.48550/ARXIV.1810.04805, https://arxiv.org/abs/1810.04805
Dong, X., Liu, L., Musial, K., Gabrys, B.: NATS-bench: benchmarking NAS algorithms for architecture topology and size. IEEE Trans. Pattern Anal. Mach. Intell. 44(7), 3634–3646 (2021)
Dong, X., Yang, Y.: NAS-Bench-201: extending the scope of reproducible neural architecture search. In: Proceedings of International Conference Learning Representations (ICLR) (2020)
Dosovitskiy, A., et al.: An image is worth 16\(\times \)16 words: transformers for image recognition at scale (2020). https://doi.org/10.48550/ARXIV.2010.11929, https://arxiv.org/abs/2010.11929
Fonseca, C., Paquete, L., Lopez-Ibanez, M.: An improved dimension-sweep algorithm for the hypervolume indicator. In: 2006 IEEE International Conference on Evolutionary Computation, pp. 1157–1163 (2006). https://doi.org/10.1109/CEC.2006.1688440
Gong, C., et al.: NASVit: neural architecture search for efficient vision transformers with gradient conflict aware supernet training. In: International Conference on Learning Representations (2022). https://openreview.net/forum?id=Qaw16njk6L
Gong, M., Jiao, L., Du, H., Bo, L.: Multiobjective immune algorithm with nondominated neighbor-based selection. Evol. Comput. 16(2), 225–255 (2008). https://doi.org/10.1162/evco.2008.16.2.225
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016). https://doi.org/10.1109/CVPR.2016.90
Holland, J.H.: Genetic algorithms. Scholarpedia 7, 1482 (2012)
Kennedy, J., Eberhart, R.: Particle swarm optimization. In: Proceedings of ICNN 1995 - International Conference on Neural Networks, vol. 4, pp. 1942–1948 (1995). https://doi.org/10.1109/ICNN.1995.488968
Kukkonen, S., Lampinen, J.: Gde3: the third evolution step of generalized differential evolution. In: 2005 IEEE Congress on Evolutionary Computation, vol. 1, pp. 443–450 (2005). https://doi.org/10.1109/CEC.2005.1554717
Li, M., Yang, S., Liu, X.: Bi-goal evolution for many-objective optimization problems. Artif. Intell. 228, 45–65 (2015). https://doi.org/10.1016/j.artint.2015.06.007, https://www.sciencedirect.com/science/article/pii/S0004370215000995
Liu, H., Simonyan, K., Yang, Y.: DARTS: differentiable architecture search. CoRR abs/1806.09055 (2018). https://arxiv.org/abs/1806.09055
Lu, Z., Cheng, R., Jin, Y., Tan, K.C., Deb, K.: Neural architecture search as multiobjective optimization benchmarks: problem formulation and performance assessment. arXiv e-prints arXiv:2208.04321 (2022)
Lu, Z., et al.: NSGA-NET: a multi-objective genetic algorithm for neural architecture search. CoRR abs/1810.03522 (2018). https://arxiv.org/abs/1810.03522
Mehrotra, A., et al.: NAS-bench-ASR: reproducible neural architecture search for speech recognition. In: Proceedings of International Conference Learning Representations (ICLR) (2021)
Qin, Y., Zhang, Z., Wang, X., Zhang, Z., Zhu, W.: NAS-bench-graph: benchmarking graph neural architecture search. arXiv preprint arXiv:2206.09166 (2022)
Siems, J., Zimmer, L., Zela, A., Lukasik, J., Keuper, M., Hutter, F.: NAS-bench-301 and the case for surrogate benchmarks for neural architecture search. CoRR abs/2008.09777 (2020). https://arxiv.org/abs/2008.09777
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2014). https://doi.org/10.48550/ARXIV.1409.1556, https://arxiv.org/abs/1409.1556
Storn, R., Price, K.V.: Differential evolution - a simple and efficient heuristic for global optimization over continuous spaces. J. Global Optim. 11, 341–359 (1997)
Su, X., et al.: Prioritized architecture sampling with Monto-Carlo tree search. In: Proceedings of the IEEE Conference on Computer Vision Pattern Recognition (CVPR) (2021)
Tan, M., Chen, B., Pang, R., Vasudevan, V., Le, Q.V.: MnasNet: platform-aware neural architecture search for mobile. CoRR abs/1807.11626 (2018)
Vaswani, A., et al.: Attention is all you need (2017). https://doi.org/10.48550/ARXIV.1706.03762, https://arxiv.org/abs/1706.03762
Wang, H., et al.: HAT: hardware-aware transformers for efficient natural language processing. CoRR abs/2005.14187 (2020)
Xiang, Y., Zhou, Y., Li, M., Chen, Z.: A vector angle-based evolutionary algorithm for unconstrained many-objective optimization. Trans. Evol. Comput. 21(1), 131–152 (2017). https://doi.org/10.1109/TEVC.2016.2587808
Ying, C., Klein, A., Christiansen, E., Real, E., Murphy, K., Hutter, F.: NAS-bench-101: towards reproducible neural architecture search. In: Proceedings of the International Conference on Machine Learning (ICML) (2019)
Zhang, X., Tian, Y., Jin, Y.: A knee point-driven evolutionary algorithm for many-objective optimization. IEEE Trans. Evol. Comput. 19(6), 761–776 (2015). https://doi.org/10.1109/TEVC.2014.2378512
Zitzler, E., Künzli, S.: Indicator-based selection in multiobjective search. In: Yao, X., et al. (eds.) PPSN 2004. LNCS, vol. 3242, pp. 832–842. Springer, Heidelberg (2004). https://doi.org/10.1007/978-3-540-30217-9_84
Zitzler, E., Laumanns, M., Thiele, L.: SPEA 2: improving the strength pareto evolutionary algorithm (2001)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Liu, X. (2023). The Utilities of Evolutionary Multiobjective Optimization for Neural Architecture Search – An Empirical Perspective. In: Pan, L., Zhao, D., Li, L., Lin, J. (eds) Bio-Inspired Computing: Theories and Applications. BIC-TA 2022. Communications in Computer and Information Science, vol 1801. Springer, Singapore. https://doi.org/10.1007/978-981-99-1549-1_15
Download citation
DOI: https://doi.org/10.1007/978-981-99-1549-1_15
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-1548-4
Online ISBN: 978-981-99-1549-1
eBook Packages: Computer ScienceComputer Science (R0)