Abstract
The privacy and security of users’ data have been a concern in the last few years. New techniques like federated learning have appeared to allow the training of machine learning models without sharing the users’ personal data. These systems have a lot of variables that can change the outcome of the models. Studies have been made to explore the effect of these variables and their importance. However, those studies only focus on machine learning models, namely deep learning. This paper explores the impact of the federation size in unbalanced data using a genetic programming model for image classification. The results show that the federation size can have impact on the contributions of each client, and the dataset size can influence the quality of the individuals.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Li, Q., et al.: A survey on federated learning systems: vision, hype and reality for data privacy and protection. IEEE Trans. Knowl. Data Eng. 35, 3347 (2023)
European Union. General Data Protection Regulation. https://gdpr.eu/
Zhu, H., Xu, J., Liu, S., Jin, Y.: Federated learning on non-IID data: a survey. arXiv (2021)
Ahvanooey, M., Li, Q., Wu, M., Wang, S.: A survey of genetic programming and its applications. KSII Trans. Internet Inf. Syst. 13 (2019)
Khan, A., Qureshi, A.S., Wahab, N., Hussain, M., Hamza, M.Y.: A recent survey on the applications of genetic programming in image processing. arXiv (2019)
Bi, Y., Xue, B., Zhang, M.: Genetic programming with image-related operators and a flexible program structure for feature learning in image classification. IEEE Trans. Evol. Comput. 25, 87 (2021)
McMahan, H.B., Moore, E., Ramage, D., Hampson, S., Arcas, B.A.: Communication-efficient learning of deep networks from decentralized data. In: Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (2016)
Mahlool, D.H., Abed, M.H.: A comprehensive survey on federated learning: concept and applications. In: Shakya, S., Ntalianis, K., Kamel, K.A. (eds.) Mobile Computing and Sustainable Informatics. LNDECT, vol. 126, pp. 539–553. Springer, Singapore (2022). https://doi.org/10.1007/978-981-19-2069-1_37
Sheller, M.J., et al.: Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data. Sci. Rep. 10, 12598 (2020)
Gong, B., Xing, T., Liu, Z., Xi, W., Chen, X.: Adaptive client clustering for efficient federated learning over non-IID and imbalanced data. IEEE Trans. Big Data 1 (2022)
Ge, N., Li, G., Zhang, L., Liu, Y.: Failure prediction in production line based on federated learning: an empirical study. J. Intell. Manuf. 33, 2277 (2022)
Gong, Y.-J., et al.: Distributed evolutionary algorithms and their models: a survey of the state-of-the-art. Appl. Soft. Comput. 34, 286 (2015)
Bremer, J., Lehnhoff, S.: Fully distributed Cartesian genetic programming. In: Advances in Practical Applications of Agents, Multi-Agent Systems, and Complex Systems Simulation. The PAAMS Collection: 20th International Conference, pp. 36–49 (2022)
Jahan, M., Hashem, M.M.A., Shahriar, G.A.: Distributed evolutionary computation: a new technique for solving large number of equations. Int. J. Parallel Distrib. Syst. (2013)
Durillo, J.J., Zhang, Q., Nebro, A.J., Alba, E.: Distribution of Computational Effort in Parallel MOEA/D. In: Coello, C.A.C. (ed.) LION 2011. LNCS, vol. 6683, pp. 488–502. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-25566-3_38
Pereira, H., Ribeiro, B., Gomes, L., Vale, Z.: CECOS: a centralized management platform supported by distributed services to represent and manage resources aggregation entities and its end-users in a smart grid context. IFAC-PapersOnLine 55, 309 (2022)
Somu, N., Raman, M.R.G., Ramamritham, K.: A deep learning framework for building energy consumption forecast. Renew. Sustain. Energy Rev. 137, 110591 (2021)
Tran, B., Sudusinghe, C., Nguyen, S., Alahakoon, D.: Building interpretable predictive models with context-aware evolutionary learning. Appl. Soft Comput. 132, 109854 (2023)
Faia, R., Faria, P., Vale, Z., Spinola, J.: Demand response optimization using particle swarm algorithm considering optimum battery energy storage schedule in a residential house. MDPI Energies 12, 1645 (2019)
Teixeira, N., Barreto, R., Gomes, L., Faria, P., Vale, Z.: A trustworthy building energy management system to enable direct IoT devices’ participation in demand response programs. MDPI Electron. 11, 897 (2022)
Caldas, S., et al.: LEAF: a benchmark for federated settings. arXiv (2018)
Acknowledgements
The present work has received funding from European Regional Development Fund through COMPETE 2020 - Operational Programme for Competitiveness and Internationalisation through the P2020 Project F4iTECH (ANI|P2020 POCI-01-0247-FEDER-181419), and has been developed under the EUREKA - CELTIC-NEXT Project F4iTECH (C2021/1-10), we also acknowledge the work facilities and equipment provided by GECAD research center (UIDB/00760/2020) to the project team.
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 Switzerland AG
About this paper
Cite this paper
Ribeiro, B., Gomes, L., Faia, R., Vale, Z. (2023). Federated Genetic Programming: A Study About the Effects of Non-IID and Federation Size. In: Ossowski, S., Sitek, P., Analide, C., Marreiros, G., Chamoso, P., Rodríguez, S. (eds) Distributed Computing and Artificial Intelligence, 20th International Conference. DCAI 2023. Lecture Notes in Networks and Systems, vol 740. Springer, Cham. https://doi.org/10.1007/978-3-031-38333-5_20
Download citation
DOI: https://doi.org/10.1007/978-3-031-38333-5_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-38332-8
Online ISBN: 978-3-031-38333-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)