Abstract
Federated Learning decreases privacy risks when training Machine Learning (ML) models on distributed data, as it removes the need for sharing and centralizing sensitive data. However, this learning paradigm can also influence the effectiveness of the obtained prediction models. In this paper, we specifically study Neural Networks, as a powerful and popular ML model, and contrast the impact of Federated Learning on the effectiveness compared to a centralized approach – when data is aggregated at one place before processing – to assess to what extent Federated Learning is suited as a replacement. We also analyze the effect of non-independent and identically distributed (non-iid) data on effectiveness and convergence speed (efficiency) of Federated Learning. Based on this, we show in which scenarios (depending on the dataset, the number of nodes in the setting and data distribution) Federated Learning can be successfully employed.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
References
McMahan, B., Moore, E., Ramage, D., Hampson, S., y Arcas, B.A.: Communication-efficient learning of deep networks from decentralized data. In: International Conference on Artificial Intelligence and Statistics, Fort Lauderdale, FL, USA, (2017). PMLR
Sheller, M.J., Reina, G.A., Edwards, B., Martin, J., Bakas, S.: Multi-institutional deep learning modeling without sharing patient data: a feasibility study on brain tumor segmentation. In: International Workshop on Brain Lesion (BrainLes), in conjunction with MICCAI (2018)
Rieke, N., Hancox, J., Li, W., et al.: The future of digital health with federated learning. NPJ Digit. Med. 3(1) (2020)
Konečný, J., McMahan, H.B., Yu, F.X. Richtárik, P., Suresh, A.T., Bacon, D.: Federated learning: strategies for improving communication efficiency. In: NIPS Workshop on Private Multi-Party Machine Learning (2016)
Nishio, T., Yonetani, R.: Client selection for federated learning with heterogeneous resources in mobile edge. In: IEEE International Conference on Communications (2019)
Sattler, F., Wiedemann, S., Müller, K.-R., Samek, W.: Robust and communication-efficient federated learning from non-i.i.d. data. IEEE Trans. Neural Netw. Learn. Syst. (2019)
Lyu, L., Han, Yu., Zhao, J., Yang, Q.: Threats to Federated Learning. Springer, Cham (2020)
Truex, S., Liu, L., Gursoy, M., Lei, Yu., Wei, W.: Demystifying membership inference attacks in machine learning as a service. IEEE Trans. Serv. Comput. (2019)
Nilsson, A., Smith, S., Ulm, G., Gustavsson, E., Jirstrand, M.: A performance evaluation of federated learning algorithms. In: Workshop on Distributed Infrastructures for Deep Learning. ACM (2018)
Shokri, R., Stronati, M., Song, C., Shmatikov, V.: Membership inference attacks against machine learning models. In: IEEE Symposium on Security and Privacy (SP) (2017)
Marcano-Cedeño, A., Buendía-Buendía, F.S., Andina, D.: Breast cancer classification applying artificial metaplasticity. In: Bioinspired Applications in Artificial and Natural Computation. Springer, Berlin, Heidelberg (2009)
Acknowledgments
This work was partially funded from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 826078 (FeatureCloud). SBA Research (SBA-K1) is a COMET Centre within the COMET – Competence Centers for Excellent Technologies Programme and funded by BMK, BMDW, and the federal state of Vienna. The COMET Programme is managed by FFG.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Pustozerova, A., Rauber, A., Mayer, R. (2021). Training Effective Neural Networks on Structured Data with Federated Learning. In: Barolli, L., Woungang, I., Enokido, T. (eds) Advanced Information Networking and Applications. AINA 2021. Lecture Notes in Networks and Systems, vol 226. Springer, Cham. https://doi.org/10.1007/978-3-030-75075-6_32
Download citation
DOI: https://doi.org/10.1007/978-3-030-75075-6_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-75074-9
Online ISBN: 978-3-030-75075-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)