Abstract
Federated learning is one computation paradigm used to address privacy preservation and efficient collaboration computing nowadays. Especially, in the environment where edge devices are facing different data scenarios, it is a challenge to enhance the prediction model accuracy. Since the data distributions on different edge devices might not be independent identical distributions, and also due to the communication obstacles existing in the modern complicated wireless world, it is an essential problem to sample which client devices to contribute to the server learning model. In this paper, instead of making the assumption on uniform distributed data sources, we assume the agnostic data distribution presumption. One indicator called client reward is defined applicable on the proposed client sampling algorithm. Combing with the redefined loss functions on the agnostic data distribution, a novel client sampling scheme is proposed and tested on real world datasets. The experiment results show that the client sampling scheme improves prediction accuracy on unbalanced data sources from different edge devices and achieves reasonable computing efficiency.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Gao, Y., Iqbal, S., et al.: Performance and power analysis of high-density multi-GPGPU architectures: a preliminary case study. In: IEEE 17th HPCC (2015)
Qiu, M., Ming, Z., Li, J., Liu, S., Wang, B., Lu, Z.: Three-phase time-aware energy minimization with DVFS and unrolling for chip multiprocessors. J. Syst. Architect. 58(10), 439–445 (2012)
Zhang, Z., Wu, J., et al.: Jamming ACK attack to wireless networks and a mitigation approach. In: IEEE GLOBECOM Conference, pp. 1–5 (2008)
Su, H., Qiu, M., Wang, H.: Secure wireless communication system for smart grid with rechargeable electric vehicles. IEEE Commun. Mag. 50(8), 62–68 (2012)
Qiu, M., Ming, Z., Li, J., Liu, J., Quan, G., Zhu, Y.: Informer homed routing fault tolerance mechanism for wireless sensor networks. J. of Systems Archi. 59(4–5), 260–270 (2013)
Gai, K., Qiu, M., Thuraisingham, B., Tao, L.: Proactive attribute-based secure data schema for mobile cloud in financial industry. In: IEEE 17th HPCC (2015)
Caldas, S., Konečny, J., McMahan, H.B., Talwalkar, A.: Expanding the reach of federated learning by reducing client resource requirements (2018). arXiv:1812.07210
Konečný, J., McMahan, H.B., Yu, F.X., Richtárik, P., Suresh, A.T., Bacon, D.: Federated learning: strategies for improving communication efficiency (2016). arXiv:1610.05492
Hamer, J., Mohri, M., Suresh, A.T.: FedBoost: a communication-efficient algorithm for federated learning. In: Proceedings of the 37th International Conference on Machine Learning, PMLR 119, pp. 3973–3983 (2020)
McMahan, 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, PMLR 54:1273–1282 (2017)
Reisizadeh, A., Mokhtari, A., Hassani, H., Jadbabaie, A., Pedarsani, R.: FedPAQ: a communication-efficient federated learning method with periodic averaging and quantization. In: Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, PMLR 108:2021–2031 (2020)
Tao, L., Golikov, S., et al.: A reusable software component for integrated syntax and semantic validation for services computing. In: IEEE Symposium on Service-Oriented System Engineering, pp. 127–132 (2015)
Zhao, H., Chen, M., et al.: A novel pre-cache schema for high performance Android system. Futur. Gener. Comput. Syst. 56, 766–772 (2016)
Li, J., Qiu, M., Niu, J., et al.: Feedback dynamic algorithms for preemptable job scheduling in cloud systems. In: IEEE/WIC/ACM Conference on Web Intelligence (2010)
Tang, X., Li, K., et al.: A hierarchical reliability-driven scheduling algorithm in grid systems. J. Parallel Distrib. Comput. 72(4), 525–535 (2012)
Qiu, H., Qiu, M., Memmi, G., Ming, Z., Liu, M.: A dynamic scalable blockchain based communication architecture for IoT. In: Qiu, M. (ed.) SmartBlock 2018. LNCS, vol. 11373, pp. 159–166. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-05764-0_17
Zhang, K., Kong, J., Qiu, M., Song, G.: Multimedia layout adaptation through grammatical specifications. Multimedia Syst. 10(3), 245–260 (2005). https://doi.org/10.1007/s00530-004-0155-2
Thakur, K., Qiu, M., Gai, K., Ali, M.: An investigation on cyber security threats and security models. In: IEEE CSCloud (2015)
Gai, K., Qiu, M., Sun, X., Zhao, H.: Security and privacy issues: a survey on FinTech. In: Qiu, M. (ed.) SmartCom 2016. LNCS, vol. 10135, pp. 236–247. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-52015-5_24
Gai, K., Qiu, M.: Optimal resource allocation using reinforcement learning for IoT content-centric services. Appl. Soft Comput. 70, 12–21 (2018)
Sahu, A.K., Li, T., Sanjabi, M.: Federated optimization for heterogeneous networks (2021). arXiv:1812.06127
Zhou, Y., Qing, Y., Lv, J.: Communication-efficient federated learning with compensated overlap-FedAvg (2021). arXiv:2012.06706
Shi, W., Zhou, S., Niu, Z.: Joint device scheduling and resource allocation for latency constrained wireless federated learning. IEEE Trans. Wireless Communications 20(1), 453–467 (2020)
Chang, W.T., Tandon, R.: Communication efficient federated learning over multiple access channels (2021). arXiv:2001.08737
Nishio, T., Yonetani, R.: Client selection for federated learning with heterogeneous resources in mobile edge. In: Proceedings of the 2019 IEEE International Conference on Communications (ICC). Piscataway, pp. 1–7. IEEE (2019)
Yoshida, N., Nishio, T., Morikura, M.: Hybrid-FL for wireless networks: cooperative learning mechanism using non-IID data. In: Proceedings of the 2020 IEEE International Conference on Communications (ICC). Piscataway, pp. 1–7. IEEE (2020)
Mohri, M., Sivek, G., Suresh, A.T.: Agnostic federated learning. In: Proceedings of the 36th International Conference on Machine Learning, PMLR 97, pp. 4615–4625 (2019)
Anand, R., Mehrotra, K.G., Mohan, C.K., Ranka, S.: An improved algorithm for neural network classification of imbalanced training sets. IEEE Trans. on Neural Networks 4(6), 962–969 (1993)
Yang, M., Wong, A., Zhu, H., Wang, H., Qian, H.: Federated learning with class imbalance reduction (2020) arXiv: 2011.11266
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
Chen, B., Zheng, X., Zhu, Y., Qiu, M. (2022). A Novel Client Sampling Scheme for Unbalanced Data Distribution Under Federated Learning. In: Qiu, M., Gai, K., Qiu, H. (eds) Smart Computing and Communication. SmartCom 2021. Lecture Notes in Computer Science, vol 13202. Springer, Cham. https://doi.org/10.1007/978-3-030-97774-0_40
Download citation
DOI: https://doi.org/10.1007/978-3-030-97774-0_40
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-97773-3
Online ISBN: 978-3-030-97774-0
eBook Packages: Computer ScienceComputer Science (R0)