Blockchain-Assisted Semi-Centralized Federated Learning Framework

Shi Hongjian; Ma Ruhui; Zhang Weishan; Guan Haibing

doi:10.7544/issn1000-1239.202330286

Journal of Computer Research and Development > 2023 > 60(11): 2567-2582. > DOI: 10.7544/issn1000-1239.202330286 CSTR: 32373.14.issn1000-1239.202330286

Shi Hongjian, Ma Ruhui, Zhang Weishan, Guan Haibing. Blockchain-Assisted Semi-Centralized Federated Learning Framework[J]. Journal of Computer Research and Development, 2023, 60(11): 2567-2582. DOI: 10.7544/issn1000-1239.202330286

Citation:

PDF (1429 KB)

Blockchain-Assisted Semi-Centralized Federated Learning Framework

Shi Hongjian^{1, 2,},
Ma Ruhui^{1, 2, ,},
Zhang Weishan³,
Guan Haibing^{1, 2}

1.
School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai 200240
2.
Shanghai Key Laboratory of Scalable Computing and Systems, Shanghai 200240
3.
Qingdao Institute of Software, College of Computer Science and Technology, China University of Petroleum (East China), Qingdao, Shandong 266580

Funds: This work was supported by Internet of Things Special Subject Program from Wuxi IoT Innovation Promotion Center (2022SP-T13-C) and the Industry-university-research Cooperation Funding Project from the Eighth Research Institute in China Aerospace Science and Technology Corporation (USCAST2022-17).

More Information

Author Bio:
Shi Hongjian: born in 1998. PhD candidate. His main research interests include distributed machine learning and AI systems

Ma Ruhui: born in 1984. PhD, associate professor, PhD supervisor. His main research interests include cloud computing systems, AI systems, and machine learning

Zhang Weishan: born in 1970. PhD, professor, PhD supervisor. His main research interests include big data processing, AI, and middleware for Internet of things

Guan Haibing: born in 1971. PhD, professor, PhD supervisor. His main research interests include cloud/distributed computing and machine learning
Received Date: April 02, 2023
Revised Date: June 12, 2023
Available Online: July 12, 2023

Graphical Abstract

Abstract

Abstract

With the development of network technology, building a trusted new-generation information management system is necessary. Blockchain technology provides a decentralized, transparent, and tamper-proof distributed base. On the other hand, with the development of artificial intelligence technology, data islands have been a common issue in the field of network data computing. The distrust among developers has made it difficult to jointly utilize all parties’ data for collaborative training. Although federated learning provides data privacy protection, there are still hidden dangers in server-side security. The traditional methods replace the server in the federated learning framework with a blockchain system to provide a tamperproof global model database. However, this approach does not utilize all available network connections in the Internet of things scenario and lacks a block structure design for federated learning tasks. We propose a blockchain-assisted semi-centralized federated learning framework. Starting from the requirements of the Internet of things scenario, our approach constructs a semi-centralized Internet of things structure and utilizes all trusted network connections to support federated learning tasks. At the same time, our approach constructs a tamper-proof model database for untrusted and remote clients through blockchain technology. Compared with traditional blockchain federated learning frameworks, our approach has a smaller communication overhead and better universality. The framework includes two major designs. The semi-centralized federated learning framework reduces the communication overhead brought by aggregation through trusted connections between clients, and stores client models through blockchain for aggregation on remote or untrusted clients to improve the universality and performance of local models. The design of blockchain blocks for federated learning tasks can support the needs of underlying federated learning training. Experiments have shown that this framework has an accuracy improvement at least 8% compared with traditional federated learning algorithms on multiple datasets, and significantly reduces the communication overhead caused by the waiting aggregation process between clients, providing guidance for the deployment of blockchain federated learning systems in practical scenarios.
- Internet of things,
- blockchain system,
- federated learning,
- semi-centralized structure,
- model aggregation

FullText(HTML)

References (54)

References

[1]	Yang Yang, Ma Mulei, Wu Hequan, et al. 6G network AI architecture for everyone-centric customized services[J/OL]. IEEE Network, 2022: 1−10. [2023-05-28].https://ieeexplore.ieee.org/document/9839652
[2]	Zhang Rui, Chu Xuesen, Ma Ruhui, et al. OSTTD: Offloading of splittable tasks with topological dependence in multi-tier computing networks[J]. IEEE Journal on Selected Areas in Communications, 2023, 41(2): 555−568 doi: 10.1109/JSAC.2022.3227023
[3]	Akabane A T, Immich R, Pazzi R W, et al. TRUSTed: A distributed system for information management and knowledge distribution in VANETs[C] //Proc of 2018 IEEE Symp on Computers and Communications. Piscataway, NJ: IEEE, 2018: 1−6
[4]	Yuan Shijing, Li Jie, Wu Chentao. JORA: Blockchain-based efficient joint computing offloading and resource allocation for edge video streaming systems[J]. Journal of Systems Architecture, 2022, 133: 102740 doi: 10.1016/j.sysarc.2022.102740
[5]	Lin Yangfei, Li Jie, Kimura S, et al. Consortium blockchain-based public integrity verification in cloud storage for IoT[J]. IEEE Internet of Things Journal, 2021, 9(5): 3978−3987
[6]	Zhang Weishan, Sun Gang, Xu Liang, et al. A trustworthy safety inspection framework using performance-security balanced blockchain[J]. IEEE Internet of Things Journal, 2022, 9(11): 8178−8190 doi: 10.1109/JIOT.2021.3121512
[7]	Shi Hongjian, Wang Hao, Ma Ruhui, et al. Robust searching-based gradient collaborative management in intelligent transportation system[J/OL]. ACM Transactions on Multimedia Computing, Communications, and Applications, 2022[2023-05-28].https://dl.acm.org/doi/10.1145/3549939
[8]	Zheng Lianmin, Li Zhuohan, Zhang Hao, et al. Alpa: Automating inter- and intra-operator parallelism for distributed deep learning[C] //Proc of the 16th USENIX Symp on Operating Systems Design and Implementation. Berkeley, CA: USENIX Association, 2022: 559−578
[9]	Zhang Jiaru, Hua Yang, Song Tao, et al. Improving Bayesian neural networks by adversarial sampling[C] //Proc of the AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2022, 36(9): 10110−10117
[10]	Du Zhaoyang, Wu C, Yoshinaga T, et al. Federated learning for vehicular Internet of things: Recent advances and open issues[J]. IEEE Open Journal of the Computer Society, 2020, 1: 45−61 doi: 10.1109/OJCS.2020.2992630
[11]	Zhang Jianqing, Hua Yang, Wang Hao, et al. FedALA: Adaptive local aggregation for personalized federated learning[C]//Proc of the AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2023, 37(9):11237−11244
[12]	Guo Hanxi, Wang Hao, Song Tao, et al. Siren: Byzantine-robust federated learning via proactive alarming[C]//Proc of ACM Symp on Cloud Computing. New York: ACM, 2021: 47−60
[13]	Zhang Weishan, Zhou Tao, Lu Qinghua, et al. Dynamic-fusion-based federated learning for COVID-19 detection[J]. IEEE Internet of Things Journal, 2021, 8(21): 15884−15891 doi: 10.1109/JIOT.2021.3056185
[14]	Qu Youyang, Uddin M P, Gan Chenquan, et al. Blockchain-enabled federated learning: A survey[J]. ACM Computing Surveys, 2023, 55(4): 70: 1−70: 35
[15]	Issa W, Moustafa N, Turnbull B P, et al. Blockchain-based federated learning for securing Internet of things: A comprehensive survey[J]. ACM Computing Surveys, 2023, 55(9): 191: 1−191: 43
[16]	Singh S K, Yang L T, Park J H. FusionFedBlock: Fusion of blockchain and federated learning to preserve privacy in industry 5.0[J]. Information Fusion, 2023, 90: 233−240 doi: 10.1016/j.inffus.2022.09.027
[17]	Zhang Weishan, Lu Qinghua, Yu Qiuyu, et al. Blockchain-based federated learning for device failure detection in industrial IoT[J], IEEE Internet of Things Journal, 2021, 8(7): 5926−5937
[18]	Guo Shaoyong, Zhang Keqin, Gong Bei, et al. Sandbox computing: A data privacy trusted sharing paradigm via blockchain and federated learning[J]. IEEE Transactions on Computers, 2023, 72(3): 800−810
[19]	Lu Yunlong, Huang Xiaohong, Zhang Ke, et al. Blockchain and federated learning for 5G beyond[J]. IEEE Network, 2021, 35(1): 219−225 doi: 10.1109/MNET.011.1900598
[20]	Feng Lei, Zhao Yiqi, Guo Shaoyong, et al. BAFL: A blockchain-based asynchronous federated learning framework[J]. IEEE Transactions on Computers, 2022, 71(5): 1092−1103 doi: 10.1109/TC.2021.3072033
[21]	Gao Liang, Li Li, Chen Yingwen, et al. FGFL: A blockchain-based fair incentive governor for federated learning[J]. Journal of Parallel and Distributed Computing, 2022, 163: 283−299 doi: 10.1016/j.jpdc.2022.01.019
[22]	Nguyen D C, Hosseinalipour S, Love D J, et al. Latency optimization for blockchain-empowered federated learning in multi-server edge computing[J]. IEEE Journal of Selected Areas in Communications, 2022, 40(12): 3373−3390 doi: 10.1109/JSAC.2022.3213344
[23]	Qu Youyang, Gao Longxiang, Xiang Yong, et al. FedTwin: Blockchain-enabled adaptive asynchronous federated learning for Digital Twin networks[J]. IEEE Network, 2022, 36(6): 183−190 doi: 10.1109/MNET.105.2100620
[24]	Shayan M, Fung C, Yoon C J M, et al. Biscotti: A blockchain system for private and secure federated learning[J]. IEEE Transactions on Parallel and Distributed Systems, 2021, 32(7): 1513−1525 doi: 10.1109/TPDS.2020.3044223
[25]	Wang Yuntao, Peng Haixia, Su Zhou, et al. A platform-free proof of federated learning consensus mechanism for sustainable blockchains[J]. IEEE Journal of Selected Areas in Communications, 2022, 40(12): 3305−3324 doi: 10.1109/JSAC.2022.3213347
[26]	Wang Weilong, Wang Yingjie, Huang Yan, et al. Privacy protection federated learning system based on blockchain and edge computing in mobile crowdsourcing[J]. Computer Networks, 2022, 215: 109206 doi: 10.1016/j.comnet.2022.109206
[27]	Wan Yichen, Qu Youyang, Gao Longxiang, et al. Privacy-preserving blockchain-enabled federated learning for B5G-Driven edge computing[J]. Computer Networks, 2022, 204: 108671 doi: 10.1016/j.comnet.2021.108671
[28]	Ruckel T, Sedlmeir J, Hofmann P. Fairness, integrity, and privacy in a scalable blockchain-based federated learning system[J]. Computer Networks, 2022, 202: 108621 doi: 10.1016/j.comnet.2021.108621
[29]	周炜,王超,徐剑,等. 基于区块链的隐私保护去中心化联邦学习模型[J]. 计算机研究与发展,2022,59(11):2423−2436 doi: 10.7544/issn1000-1239.20220470 Zhou Wei, Wang Chao, Xu Jian, et al. Privacy-preserving and decentralized federated learning model based on the blockchain[J]. Journal of Computer Research and Development, 2022, 59(11): 2423−2436 (in Chinese) doi: 10.7544/issn1000-1239.20220470
[30]	Li Zonghang, Yu Hongfang, Zhou Tianyao, et al. Byzantine resistant secure blockchained federated learning at the edge[J]. IEEE Network, 2021, 35(4): 295−301 doi: 10.1109/MNET.011.2000604
[31]	Tang Fengxiao, Wen Cong, Luo Linfeng, et al. Blockchain-based trusted traffic offloading in space-air-ground integrated networks (SAGIN): A federated reinforcement learning approach[J]. IEEE Journal of Selected Areas in Communications, 2022, 40(12): 3501−3516 doi: 10.1109/JSAC.2022.3213317
[32]	Cui Laizhong, Su Xiaoxin, Zhou Yipeng. A fast blockchain-based federated learning framework with compressed communications[J]. IEEE Journal of Selected Areas in Communications, 2022, 40(12): 3358−3372 doi: 10.1109/JSAC.2022.3213345
[33]	Pokhrel S R, Choi J. Federated learning with blockchain for autonomous vehicles: Analysis and design challenges[J]. IEEE Transactions on Computers, 2020, 68(8): 4734−4746
[34]	Li Yuzheng, Chen Chuan, Liu Nan, et al. A blockchain-based decentralized federated learning framework with committee consensus[J]. IEEE Network, 2021, 35(1): 234−241 doi: 10.1109/MNET.011.2000263
[35]	Feng Lei, Yang Zhixiang, Guo Shaoyong, et al. Two-layered blockchain architecture for federated learning over the mobile edge network[J]. IEEE Network, 2022, 36(1): 45−51 doi: 10.1109/MNET.011.2000339
[36]	Li Jun, Shao Yumeng, Wei Kang, et al. Blockchain assisted decentralized federated learning (BLADE-FL): Performance analysis and resource allocation[J]. IEEE Transactions on Parallel and Distributed Systems, 2022, 33(10): 2401−2415 doi: 10.1109/TPDS.2021.3138848
[37]	Zhang Weishan, Yu Fa, Wang Xiao, et al. R2Fed: Resilient reinforcement federated learning for industrial applications[J/OL]. IEEE Transactions on Industrial Informatics, 2022[2023-05-28].https://ieeexplore.ieee.org/document/9950718
[38]	McMahan B, Moore E, Ramage D, et al. Communication-efficient learning of deep networks from decentralized data[C] //Proc of the 20th Int Conf on Artificial Intelligence and Statistics. New York: PMLR, 2017, 54: 1273−1282
[39]	Li Tian, Sahu A K, Zaheer M, et al. Federated optimization in heterogeneous networks[C] //Proc of Machine Learning and Systems. Indio, CA: Systems and Machine Learning Foundation, 2020: 429−450
[40]	Li Qinbin, He Bingsheng, Song D. Model-contrastive federated learning[C] //Proc of IEEE Conf on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2021: 10713−10722
[41]	Acar D A E, Zhao Yue, Navarro R M, et al. Federated learning based on dynamic regularization[C/OL] //Proc of the 9th Int Conf on Learning Representations. OpenReview. net, 2021[2023-05-28].https://openreview.net/forum?id=B7v4QMR6Z9w
[42]	Li Xiaoxiao, Jiang Meirui, Zhang Xiaofei, et al. FedBN: Federated learning on non-IID features via local batch normalization[C/OL] //Proc of the 9th Int Conf on Learning Representations. OpenReview. net, 2021[2023-05-28].https://openreview.net/forum?id=6YEQUn0QICG
[43]	Arivazhagan M G, Aggarwal V, Singh A K, et al. Federated learning with personalization layers[J/OL]. arXiv preprint, arXiv: 1912.00818, 2019[2023-05-28].https://arxiv.org/abs/1912.00818
[44]	Collins L, Hassani H, Mokhtari A, et al. Exploiting shared representations for personalized federated learning[C] //Proc of the 38th Int Conf on Machine Learning. New York: PMLR, 2021, 139: 2089−2099
[45]	Oh J, Kim S, Yun S Y. FedBABU: Towards enhanced representation for federated image classification[J/OL]. arXiv preprint, arXiv: 2106.06042, 2021[2023-05-28].https://arxiv.org/abs/2106.06042
[46]	Deng Yuyang, Kamani M M, Mahdavi M. Adaptive personalized federated learning[J/OL]. arXiv preprint, arXiv: 2003.13461, 2020[2023-05-28].https://arxiv.org/abs/2003.13461
[47]	Li Xinchun, Zhan Dechuan, Shao Yunfeng, et al. FedPHP: Federated personalization with inherited private models[C] //Proc of Machine Learning and Knowledge Discovery in Databases. Berlin: Springer, 2021, 12975: 587−602
[48]	Li Tian, Hu Shengyuan, Beirami A, et al. Ditto: Fair and robust federated learning through personalization[C] //Proc of the 38th Int Conf on Machine Learning. New York: PMLR, 2021, 139: 6357−6368
[49]	Zhang M, Sapra K, Fidler S, et al. Personalized federated learning with first order model optimization[C/OL] //Proc of the 9th Int Conf on Learning Representations. OpenReview. net, 2021[2023-05-28].https://openreview.net/forum?id=ehJqJQk9cw
[50]	Huang Yutao, Chu Lingyang, Zhou Zirui, et al. Personalized cross-silo federated learning on non-IID data[C] //Proc of the 35th AAAI Conf on Artificial Intelligence. Palo Alto, CA: AAAI, 2021: 7865−7873
[51]	Luo Jun, Wu Shandong. Adapt to adaptation: Learning personalization for cross-silo federated learning[C] //Proc of the 31st Int Joint Conf on Artificial Intelligence. California: ijcai. org, 2022: 2166−2173
[52]	Fraboni Y, Vidal R, Kameni L, et al. A general theory for federated optimization with asynchronous and heterogeneous clients updates[J/OL]. arXiv preprint, arXiv: 2206.10189, 2022[2023-05-28].https://arxiv.org/abs/2206.10189
[53]	Zalando. Fashion-MNIST[DB/OL]. [2023-04-01].https://github.com/zalandoresearch/fashion-mnist
[54]	Krizhevsky A, Nair V, Hinton G. The CIFAR-10 dataset[DB/OL]. [2023-04-01].https://www.cs.toronto.edu/~kriz/cifar.html

Cited By

Cited by

Periodical cited type(6)

1.	韩宇捷，徐志杰，杨定裕，黄波，郭健美. CDES:数据驱动的云数据库效能评估方法. 计算机科学. 2024(06): 111-117 .
2.	刘传磊，张贺，杨贺. 地铁保护区智能化巡查系统开发及应用研究. 现代城市轨道交通. 2024(09): 23-30 .
3.	董文，张俊峰，刘俊，张雷. 国产数据库在能源数字化转型中的创新应用研究. 信息通信技术与政策. 2024(10): 68-74 .
4.	阎开. 计算机检测维修与数据恢复技术及应用研究. 信息记录材料. 2023(08): 89-91 .
5.	冯丽琴，冯花平. 基于人脸识别的可控化学习数据库系统设计. 数字通信世界. 2023(10): 69-71 .
6.	张惠芹，章小卫，杜坤，李江. 基于数字孪生的高校实验室高温设备智能化监管体系的探究. 实验室研究与探索. 2023(11): 249-252+282 .