Browse > Article
http://dx.doi.org/10.9708/jksci.2022.27.11.013

Design of weighted federated learning framework based on local model validation  

Kim, Jung-Jun (Korea Institute of Robotics & Technology Convergence)
Kang, Jeon Seong (Korea Institute of Robotics & Technology Convergence)
Chung, Hyun-Joon (Korea Institute of Robotics & Technology Convergence)
Park, Byung-Hoon (Software Architect, T3Q Co., Ltd.)
Abstract
In this paper, we proposed VW-FedAVG(Validation based Weighted FedAVG) which updates the global model by weighting according to performance verification from the models of each device participating in the training. The first method is designed to validate each local client model through validation dataset before updating the global model with a server side validation structure. The second is a client-side validation structure, which is designed in such a way that the validation data set is evenly distributed to each client and the global model is after validation. MNIST, CIFAR-10 is used, and the IID, Non-IID distribution for image classification obtained higher accuracy than previous studies.
Keywords
AI; Federated Learning; Deep Learning; Mobile Computing; Object Classification;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Ding, Chuntao, et al. "Resource-aware feature extraction in mobile edge computing." IEEE Transactions on Mobile Computing Vol. 21. No. 1, pp. 321-331. 2020. DOI: 10.1109/TMC.2020.3007456   DOI
2 Karimireddy SP, Kale S, Mohri M, Reddi S, Stich S, Suresh AT. "Scaffold: Stochastic controlled averaging for federated learning." InInternational Conference on Machine Learning (PMLR.) pp. 5132-5143, Nov. 21. 2020. DOI : 10.48550/arXiv.1910.06378   DOI
3 Ren, H., Li, H., Dai, Y., Yang, K., & Lin, X.. "Querying in internet of things with privacy preserving: Challenges, solutions and opportunities." IEEE Network, Vol. 32. No. 6, pp. 144-151. 2018. DOI: 10.1109/MNET.2018.1700374   DOI
4 SSahu, Anit Kumar, et al. "On the convergence of federated optimization in heterogeneous networks." arXiv preprint arXiv:1812.06127 Dec. 3 2018. DOI : 10.48550/arXiv.1812.06127
5 Garcia, David, et al. "Analyzing gender inequality through large-scale Facebook advertising data." Proceedings of the National Academy of Sciences Vol. 115. No. 27, pp. 6958-6963, 2018. DOI: 10.1073/pnas.1717781115   DOI
6 McMahan, Brendan, and Daniel Ramage. "Federated learning: Collaborative machine learning without centralized training data." Google Research Blog 3 2017.
7 Mann Soo Hong, Seok-Kyu Kang, Jee-Hyong Lee, "Removing Out-of-Distribution Clients on Federated Model", Journal of The Korean Institute of Intelligent Systems, Vol. 30, No. 6, pp. 488-493, 2020   DOI
8 Yang, Q., Liu, Y., Chen, T. and Tong, Y. "Federated machine learning: Concept and applications." ACM Transactions on Intelligent Systems and Technology (TIST), Vol. 10. No. 2, pp. 1-19, 2019. DOI:10.1145/3298981   DOI
9 Krizhevsky, Alex, and Geoffrey Hinton. "Learning multiple layers of features from tiny images." (2009): 7.
10 Deng, Li. "The mnist database of handwritten digit images for machine learning research [best of the web]." IEEE signal processing magazine Vol. 29, No. 6, pp. 141-142. 2012. DOI: 10.1109/MSP.2012.2211477   DOI
11 Simonyan, Karen, and Andrew Zisserman. "Very deep convolutional networks for large-scale image recognition." arXiv preprint arXiv:1409.1556 (2014). DOI: 10.48550/arXiv.1409.1556
12 He, Kaiming, et al. "Deep residual learning for image recognition." Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 770-778, 2016. DOI: 10.1109/CVPR.2016.90   DOI
13 H. Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, Blaise Ag era y Arcas, "Communication-efficient learning of deep networks from decentralized data," arXiv:1602.05629, (2016) DOI: 10.48550/arXiv.1602.05629
14 Wang H, Yurochkin M, Sun Y, Papailiopoulos D, Khazaeni Y. "Federated learning with matched averaging". arXiv preprint arXiv:2002.06440. Feb. 15. 2020. DOI : 10.48550/arXiv.2002.06440