APPLICATION OF AHP FOR WEIGHTING CLIENTS IN FEDERATED LEARNING

Details

Hits: 105

Volume 6 (2), December 2023, Pages 153-162

Samir Aliyev

Azerbaijan State Oil and Industry University, Baku, Azerbaijan, This email address is being protected from spambots. You need JavaScript enabled to view it.

Abstract

Federated Learning is a branch of Machine Learning. The main idea behind it, unlike traditional Machine Learning, is that it does not require data from the clients to create a global model, so clients keep their data private. Instead, clients train their model on their own devices and send their local model to the server, where the global model is aggregated and sent back to clients. In this research work, the Federated Averaging algorithm is modified so that clients get their weights by the Analytical Hierarchal Process. Results showed that applying AHP for weighting performed better than giving clients weights solely based on their dataset size, which the Federated Averaging algorithm does.

Keywords:

Federated Learning, AHP, Geometric Mean, Client Weighting, Federated Averaging.

DOI: https://doi.org/10.32010/26166127.2023.6.2.153.162

Reference 

Aliyev, S., & Ismayilova, N. (2023, October). FL2: Fuzzy Logic for Device Selection in Federated Learning. In 2023 IEEE 17th International Conference on Application of Information and Communication Technologies (AICT) (pp. 1-6). IEEE.

Du, Z., Wu, C., Yoshinage, T., Zhong, L., & Ji, Y. (2022, October). On-device federated learning with fuzzy logic based client selection. In Proceedings of the Conference on Research in Adaptive and Convergent Systems (pp. 64-70).

Hong, M., Kang, S. K., & Lee, J. H. (2022). Weighted averaging federated learning based on example forgetting events in label imbalanced non-iid. Applied Sciences, 12(12), 5806.

Li, Y., Guo, Y., Alazab, M., Chen, S., Shen, C., & Yu, K. (2022). Joint optimal quantization and aggregation of federated learning scheme in VANETs. IEEE Transactions on Intelligent Transportation Systems, 23(10), 19852-19863.

Qi, P., Chiaro, D., Guzzo, A., Ianni, M., Fortino, G., & Piccialli, F. (2023). Model aggregation techniques in federated learning: A comprehensive survey. Future Generation Computer Systems.

Roberts, G., Rao, N. K., & Kumar, S. (1987). Logistic regression analysis of sample survey data. Biometrika, 74(1), 1-12.

Saaty, R. W. (1987). The analytic hierarchy process—what it is and how it is used. Mathematical modelling, 9(3-5), 161-176.

Sun, T., Li, D., & Wang, B. (2022). Decentralized federated averaging. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(4), 4289-4301.

Tang, Z., Shao, F., Chen, L., Ye, Y., Wu, C., & Xiao, J. (2021). Optimizing federated learning on non-IID data using local Shapley value. In Artificial Intelligence: First CAAI International Conference, CICAI 2021, Hangzhou, China, June 5–6, 2021, Proceedings, Part II 1 (pp. 164-175). Springer International Publishing.

Wilbik, A., & Grefen, P. (2021, July). Towards a federated fuzzy learning system. In 2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) (pp. 1-6). IEEE.

Xu, C., Hong, Z., Huang, M., & Jiang, T. (2022). Acceleration of federated learning with alleviated forgetting in local training. arXiv preprint arXiv:2203.02645.

Yadav, A., & Jayswal, S. C. (2013). Using geometric mean method of analytical hierarchy process for decision making in functional layout. International Journal of Engineering Research and Technology (IJERT), 2(5).

Ye, R., Xu, M., Wang, J., Xu, C., Chen, S., & Wang, Y. (2023). FedDisco: Federated Learning with Discrepancy-Aware Collaboration. arXiv preprint arXiv:2305.19229.