Abstract
This work proposes, develops, and evaluates an approach to improve the efficiency of ML models. This approach is centered on a Green AI, and the models’ efficiency is a trade-off of accuracy, time to solution, and energy consumption. This leads to a multi-objective optimization problem implemented through the Genetic Algorithms (GA). We present the GA scheme and operators designed for this work focused on the architecture and hyperparameter optimization of ML pipeline, developed to be part of an AutoML solution. GA was evaluated for the XGBoost algorithm and results show the effectiveness of the GA for this multi-objective optimization. Also, it was possible to reduce energy consumption with minimal losses of predictive performance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
- 3.
- 4.
References
Bender, E.M., Gebru, T., McMillan-Major, A., Shmitchell, S.: On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? Association for Computing Machinery, New York (2021)
Bernardo, F., Yokoyama, A., Schulze, B., Ferro, M.: Avaliação do consumo de energia para o treinamento de aprendizado de máquina utilizando single-board computers baseadas em arm. In: Anais do XXII Simpósio em Sistemas Computacionais de Alto Desempenho, pp. 60–71. SBC, Porto Alegre, RS, Brasil (2021). https://doi.org/10.5753/wscad.2021.18512
Chen, T., Guestrin, C.: XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 785–794 (2016)
Colorni, A., Dorigo, M., Maniezzo, V.: Genetic algorithms and highly constrained problems: the time-table case. In: Schwefel, H.-P., Männer, R. (eds.) PPSN 1990. LNCS, vol. 496, pp. 55–59. Springer, Heidelberg (1991). https://doi.org/10.1007/BFb0029731
David, E., Greental, I.: Genetic algorithms for evolving deep neural networks. In: GECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference, July 2014. https://doi.org/10.1145/2598394.2602287
Doke, A., Gaikwad, M.: Survey on automated machine learning (AutoML) and meta learning. In: 2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT), pp. 1–5 (2021)
Ferreira, L., Pilastri, A., Martins, C.M., Pires, P.M., Cortez, P.: A comparison of AutoML tools for machine learning, deep learning and XGBoost. In: 2021 International Joint Conference on Neural Networks (IJCNN), pp. 1–8 (2021). https://doi.org/10.1109/IJCNN52387.2021.9534091
Ferro, M., Silva, G.D., de Paula, F.B., Vieira, V., Schulze, B.: Towards a sustainable artificial intelligence: a case study of energy efficiency in decision tree algorithms. Concurrency and Computation: Practice and Experience n/a(n/a), e6815, December 2021. https://doi.org/10.1002/cpe.6815
Feurer, M., Klein, A., Eggensperger, K., Springenberg, J.T., Blum, M., Hutter, F.: Auto-sklearn: efficient and robust automated machine learning. In: Hutter, F., Kotthoff, L., Vanschoren, J. (eds.) Automated Machine Learning. TSSCML, pp. 113–134. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-05318-5_6
Ganapathy, K.: A study of genetic algorithms for hyperparameter optimization of neural networks in machine translation (2020)
Goldberg, D.E.: Genetic Algorithms in Search. 1st edn. Optimization and Machine Learning. Addison-Wesley Longman Publishing Co., Inc, USA (1989)
Hamdia, K.M., Zhuang, X., Rabczuk, T.: An efficient optimization approach for designing machine learning models based on genetic algorithm. Neural Comput. Appl. 33(6), 1923–1933 (2021)
He, X., Zhao, K., Chu, X.: AutoML: a survey of the state-of-the-art. Knowl. Based Syst. 212, 106622 (2021). https://doi.org/10.1016/j.knosys.2020.106622
Heffetz, Y., Vainshtein, R., Katz, G., Rokach, L.: DeepLine: AutoML tool for pipelines generation using deep reinforcement learning and hierarchical actions filtering. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 2103–2113. KDD 2020, Association for Computing Machinery, New York, NY, USA (2020). https://doi.org/10.1145/3394486.3403261
Holland, J.H.: Genetic algorithms. Scientific American, July 1992
Jian, W., Zhou, Y., Liu, H.: Densely connected convolutional network optimized by genetic algorithm for fingerprint liveness detection. IEEE Access 9, 2229–2243 (2021). https://doi.org/10.1109/ACCESS.2020.3047723
Johnson, F., Valderrama, A., Valle, C., Crawford, B., Soto, R., \(\tilde{\rm N}\)anculef, R.: Automating configuration of convolutional neural network hyperparameters using genetic algorithm. IEEE Access 8, 156139–156152 (2020). https://doi.org/10.1109/ACCESS.2020.3019245
Kaggle: State of data science and machine learning 2021. Technical report (2021). https://www.kaggle.com/kaggle-survey-2021
LeDell, E., Poirier, S.: H2O AutoML: Scalable automatic machine learning. In: 7th ICML Workshop on Automated Machine Learning (AutoML), July 2020
Lee, S., Kim, J., Kang, H., Kang, D.Y., Park, J.: Genetic algorithm based deep learning neural network structure and hyperparameter optimization. Appl. Sci. (2021). https://doi.org/10.3390/app11020744
Nagarajah, T., Poravi, G.: A review on automated machine learning (AutoML) systems. In: 2019 IEEE 5th International Conference for Convergence in Technology (I2CT), pp. 1–6 (2019). https://doi.org/10.1109/I2CT45611.2019.9033810
Nikitin, N.O., et al.: Automated evolutionary approach for the design of composite machine learning pipelines. Future Gener. Comput. Syst. 127, 109–125 (2022)
Olson, R.S., Bartley, N., Urbanowicz, R.J., Moore, J.H.: Evaluation of a tree-based pipeline optimization tool for automating data science. In: Proceedings of the Genetic and Evolutionary Computation Conference 2016, pp. 485–492. GECCO 2016, Association for Computing Machinery, New York, NY, USA (2016). https://doi.org/10.1145/2908812.2908918
Pfisterer, F., Coors, S., Thomas, J., Bischl, B.: Multi-objective automatic machine learning with AutoXGBoostMC (2019). https://doi.org/10.48550/ARXIV.1908.10796
Polonskaia, I.S., Nikitin, N.O., Revin, I., Vychuzhanin, P., Kalyuzhnaya, A.V.: Multi-objective evolutionary design of composite data-driven models. In: 2021 IEEE Congress on Evolutionary Computation (CEC), pp. 926–933 (2021). https://doi.org/10.1109/CEC45853.2021.9504773
Rani, R., Sharma, A.: An optimized framework for cancer classification using deep learning and genetic algorithm. J. Med. Imaging Health Inform. 7, 1851–1856 (2017). https://doi.org/10.1166/jmihi.2017.2266
Schwartz, R., Dodge, J., Smith, N.A., Etzioni, O.: Green AI. Commun. ACM 63(12), 54–63 (2020)
Strubell, E., Ganesh, A., McCallum, A.: Energy and policy considerations for deep learning in NLP. arXiv preprint arXiv:1906.02243 (2019)
Xiao, X., Yan, M., Basodi, S., Ji, C., Pan, Y.: Efficient hyperparameter optimization in deep learning using a variable length genetic algorithm (2020)
Young, S., Rose, D., Karnowski, T., Lim, S.H., Patton, R.: Optimizing deep learning hyper-parameters through an evolutionary algorithm. In: ACM Proceedings, pp. 1–5 (11 2015)
Yuan, Y., Wang, W., Coghill, G.M., Pang, W.: A novel genetic algorithm with hierarchical evaluation strategy for hyperparameter optimisation of graph neural networks. CoRR abs/2101.09300 (2021). https://arxiv.org/abs/2101.09300
Acknowledgements
This work is funded by Faperj, CAPES and LNCC-MCTI. Projects GreenAI 21-CLIMAT-07 and SUSAIN Inria Associated Teams.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Yokoyama, A.M., Ferro, M., Schulze, B. (2022). A Multi-objective Hyperparameter Optimization for Machine Learning Using Genetic Algorithms: A Green AI Centric Approach. In: Bicharra Garcia, A.C., Ferro, M., Rodríguez Ribón, J.C. (eds) Advances in Artificial Intelligence – IBERAMIA 2022. IBERAMIA 2022. Lecture Notes in Computer Science(), vol 13788. Springer, Cham. https://doi.org/10.1007/978-3-031-22419-5_12
Download citation
DOI: https://doi.org/10.1007/978-3-031-22419-5_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-22418-8
Online ISBN: 978-3-031-22419-5
eBook Packages: Computer ScienceComputer Science (R0)