A Dynamic Adaptive and Resource-Allocated Selection Method Based on TOPSIS and VIKOR in Federated Learning

Lin Li1, Wei Shi1, Shuyu Chen2, Jun Liu1, Jiangping Huang1, Pengcheng Liu3
1School of Software Engineering, Chongqing University of Posts and Telecommunications, Chongqing, China
2School of Big Data and software Engineering, Chongqing University, Chongqing, China
3Chongqing Ziguang Huashan Zhian Technology Co., Ltd., Chongqing, China

Tóm tắt

Federated learning (FL) is a decentralized and privacy-preserving machine learning technique that protects data privacy by learning models locally and not sharing datasets. However, due to limited computing resources on devices and highly heterogeneous data in practical situations, the training efficiency and resource utilization of federated learning is low. In order to resolve these challenges, we introduce a blockchain-assisted dynamic adaptive and personalized federated learning framework (TV-FedAvg) in the presence of restricted computing power resources and data heterogeneity. After each round of local training, we utilize an improved scoring model based on VIKOR and TOPSIS to comprehensively score the devices. The scores are then utilized to choose devices for participation in global aggregation and to carry out model aggregation through blockchain consensus. Furthermore, resources are reallocated for the next round to enhance resource efficiency, model fairness, and performance. Finally, we demonstrate through experimentation that TV-FedAvg outperforms other models such as pFedMe, FedAvg, Per-FedAvg, and TOPSIS in terms of both efficiency and performance.

Từ khóa


Tài liệu tham khảo

Li L, Fan Y, Tse M et al (2020) A review of applications in federated learning. Comput Ind Eng 149(5):106854 Zhang C, Xie Y, Bai H et al (2021) A survey on federated learning. Knowl-Based Syst 216(1):106775 Kairouz EBP, Mcmahan HB (2021) Advances and open problems in federated learning. Found Trends Mach Learn 14(1):1–210 Li T, Sahu AK, Talwalkar A, Smith V (2020) Federated learning: challenges, methods, and future directions. IEEE Signal Process Mag 37(3):50–60. https://doi.org/10.1109/MSP.2020.2975749 Li T, Sanjabi M, Beirami A et al (2019) Fair resource allocation in federated learning. https://doi.org/10.48550/arXiv.1905.10497 Song R, Liu D, Chen DZ et al (2022) Federated learning via decentralized dataset distillation in resource-constrained edge environments. arXiv preprint arXiv:2208.11311 Sultana A, Haque MM, Chen L et al (2022) Eiffel: efficient and fair scheduling in adaptive federated learning. IEEE Trans Parallel Distrib Syst 33(12):4282–4294 Xie M, Liu J, Chen S, Lin M (2023) A survey on blockchain consensus mechanism: research overview, current advances and future directions. Int J Intell Comput Cybern 16(2):314–340 Zehui X, Yang Z, Dusit N, Ping W, Zhu H (2017) When mobile blockchain meets edge computing. IEEE Commun Mag 56(8):33–39 Qu X, Wang S, Hu Q, Cheng X (2021) Proof of federated learning: a novel energy-recycling consensus algorithm. IEEE Trans Parallel Distrib Syst 99:1–1 Feng L, Zhao Y, Guo S, Qiu X, Yu P (2021) Blockchain-based asynchronous federated learning for internet of things. IEEE Trans Comput 99:1–1 Uddin MP, Xiang Y, Lu X, Yearwood J, Gao L (2020) Mutual information driven federated learning. IEEE Trans Parallel Distrib Syst 99:1–1 Li J, Shao Y, Wei K et al (2021) Blockchain assisted decentralized federated learning (BLADE-FL): performance analysis and resource allocation. IEEE Trans Parallel Distrib Syst 33(10):2401–2415 Chakraborty S (2023) TOPSIS and modified TOPSIS: a comparative analysis. Decis Anal J. https://doi.org/10.31224/osf.io/y39j7 Hashemi A, Dowlatshahi MB, Nezamabadi-Pour H (2021) VMFS: a VIKOR-based multi-target feature selection. Expert Syst Appl. https://doi.org/10.1016/j.eswa.2021.115224 Hu M et al (2022) AutoFL: a Bayesian game approach for autonomous client participation in federated edge learning. IEEE Trans Mob Comput. https://doi.org/10.1109/TMC.2022.3227014 Duan M, Liu D, Chen X, Liu R, Tan Y, Liang L (2021) Self-balancing federated learning with global imbalanced data in mobile systems. IEEE Trans Parallel Distrib Syst 32(1):59–71 Wu Q, Chen X, Zhou Z, Zhang J (2020) FedHome: cloud-edge based personalized federated learning for in-home health monitoring. IEEE Trans Mob Comput. https://doi.org/10.1109/TMC.2020.3045266 Wang H, Kaplan Z, Niu D, Li B (2020) Optimizing federated learning on non-IID data with reinforcement learning. IEEE INFOCOM 2020–IEEE conference on computer communications. ON, Canada, Toronto, pp 1698–1707 Yang M, Wang X, Zhu H, Wang H, Qian H (2021) Federated learning with class imbalance reduction. IEEE EUSIPCO 2021:2174–2178 Chuang Ma, Xin Ren, Guangxia Xu, Bo He (2023) FedGR: federated graph neural network for recommendation systems. Axioms 12(2):170 Li T, Sahu AK, Zaheer M et al (2018) Federated optimization in heterogeneous networks. arXiv:1812.06127 Yao X, Sun L (2020) Continual Local Training For Better Initialization of Federated Models. In: IEEE international conference on image processing (ICIP), Abu Dhabi, United Arab Emirates, 2020, pp 1736–1740 Karimireddy SP, Kale S, Mohri M, Reddi S, Stich Suresh AT (2020) Scaffold: stochastic controlled averaging for federated learning. In: International conference on machine learning, pp. 5132–5143 Nishio T, Yonetani R (2019) Client selection for federated learning with heterogeneous resources in mobile edge. In: Proc. IEEE international conference on communications, pp. 1–7 Amiri MM, Deniz G, Kulkarni SR, Poor HV (2020) Update aware device scheduling for federated learning at the wireless edge. Proc. In, IEEE international symposium on information, pp 2598–2603 Ke HC, Wang H, Zhao HW, Sun WJ (2021) Deep reinforcement learning-based computation offloading and resource allocation in security-aware mobile edge computing. Wirel Netw 27(5):3357–3373 Dinh CT, Tran NH, Nguyen TD (2020) Personalized federated learning with moreau envelopes. 2020.https://doi.org/10.48550/arXiv.2006.08848 Liu Q, Mo R, Xu X et al (2020) Multi-objective resource allocation in mobile edge computing using PAES for Internet of Things. Wireless Networks. https://doi.org/10.1007/s11276-020-02409-w Lau H, Tsang YP, Nakandala D et al (2021) Risk quantification in cold chain management: a federated learning-enabled multi-criteria decision-making methodology. Ind Manag Data Syst 121(7):1684–1703 Alamleh A et al (2023) Federated learning for IoMT applications: a standardization and benchmarking framework of intrusion detection systems. IEEE J Biomed Health Inform 27(2):878–887 Xu G, Liu Y, Khan PW (2019) Improvement of the DPoS consensus mechanism in blockchain based on vague sets. IEEE Trans Ind Inform 99:1–1 Liu J, Xie MY, Chen SY, Xu GX, Wu TS, Li W (2023) TS-REPLICA: a novel replica placement algorithm based on the entropy weight TOPSIS method in spark for multimedia data analysis. Inf Sci 626:133–148 Yang H, Zhang X, Fu K et al (2023) Comprehensive evaluation of urban water supply security based on the VIKOR-TOPSIS method. Environ Sci Pollut Res 30(3):8363–8375 Xie M, Liu J, Chen S et al (2023) Primary node election based on probabilistic linguistic term set with confidence interval in the PBFT consensus mechanism for blockchain. Complex Intell Syst 9(2):1507–1524 Deng X, Li J, Shi L et al (2020) Wireless powered mobile edge computing: dynamic resource allocation and throughput maximization. IEEE Trans Mob Comput 21(6):2271–2288 Fang M, Liu J (2020) Toward low-cost and stable blockchain networks. In: IEEE international conference on communications (ICC). IEEE, pp 1–6 Fallah A, Mokhtari A, Ozdaglar A (2020) personalized federated learning: a meta-learning approach. https://doi.org/10.48550/arXiv.2002.07948 Huang H, Guo S, Liang W, Wang K, Okabe Y (2020) Coflow-like online data acquisition from low-earth-orbit datacenters. IEEE Trans Mobile Comput 19(12):2743–2760