基于联邦学习的多技术融合数据交易方法

doi:10.19678/j.issn.1000-3428.0067954

摘要/Abstract

摘要：

数据保护的约束使得数据被限制在不同企业和组织之间，形成了众多“数据孤岛”，难以发挥其蕴含的重要价值。联邦学习的出现使得数据在组织之间共享成为可能，但利益分配方案不明确、通信成本高、中心化等问题使其难以满足数据交易场景的多方位需求。针对这些问题，提出一种基于联邦学习的多技术融合数据交易方法（MTFDT）。通过结合可信执行环境与沙普利值进行激励机制设计，并对交易过程中模型数据同步机制进行优化，提出一种基于树型拓扑结构的模型同步方案，使得同步时间复杂度由线性级降低至对数级。同时，设计基于区块链的利益分配数据和模型数据存储方案，使得交易过程信息不可篡改并能够通过溯源的方式进行追责。基于公开数据集进行仿真对比，实验结果表明，MTFDT能够实现模型训练效果的精确评估，提高利益分配的公平性，相比已有方案，模型同步时间消耗最多减少34%且对带宽要求更低。

关键词: 数据交易, 联邦学习, 区块链, 激励机制, 通信优化

Abstract:

The constraints of data protection have restricted data within different enterprises and organizations, forming several "data islands" that make it difficult to tap into their inherent important value. The emergence of Federated Learning(FL) has made data sharing between organizations possible. However, issues such as unclear benefit distribution schemes, high communication costs, and centralization make it difficult to meet the multifaceted demands of data trading scenarios. To address these issues, a Multi-Technology Fused Data Trading(MTFDT) method based on FL is proposed. In this method, the incentive mechanism is designed by combining trusted execution environments with the Shapley value. The model and data synchronization mechanism during trading are optimized using a tree-based topological structure-based model synchronization scheme, reducing the synchronization time complexity from linear to logarithmic. Simultaneously, blockchain-based benefit distribution data and model data storage solutions are designed to make the transaction information tamper-proof and accountable through traceability. Finally, simulations and comparisons are performed using public datasets. The experimental results demonstrate that MTFDT can achieve a precise evaluation of the model training effects and improve the fairness of the benefit distribution. Compared to existing solutions, the time consumption of model synchronization is reduced by up to 34%, and the bandwidth requirement is lower.

Key words: data transaction, Federated Learning(FL), blockchain, incentive system, communication optimization

刘少杰, 文斌, 王泽旭. 基于联邦学习的多技术融合数据交易方法[J]. 计算机工程, 2024, 50(3): 182-190.

Shaojie LIU, Bin WEN, Zexu WANG. Multi-Technology Fused Data Trading Method Based on Federated Learning[J]. Computer Engineering, 2024, 50(3): 182-190.

http://www.ecice06.com/CN/Y2024/V50/I3/182

图/表 16

图1 MTFDT工作流程

Fig.1 Workflow of MTFDT

图2 MTFDT中贡献评估与利益分配流程

Fig.2 Contribution evaluation and benefit distribution process in MTFDT

图3 星型拓扑结构联邦学习模型数据同步

Fig.3 Data synchronization of federated learning model with star topology structure

图4 树型拓扑结构联邦学习模型数据同步

Fig.4 Data synchronization of federated learning model with tree topology structure

图5 树型拓扑结构联邦学习模型同步过程

Fig.5 Synchronization process of federated learning model with tree topology structure

图6 数据交易场景智能合约设计

Fig.6 Smart contracts design for data transaction scenario

图7 数据存储设计

Fig.7 Data storage design

图8 不同规模数据集分布下贡献度占比结果

Fig.8 Contribution ratio results under different size dataset distributions

图9 不同节点数目条件下模型同步时间消耗对比

Fig.9 Comparison of model synchronization time consumption under different number of nodes

图10 不同带宽条件下模型同步时间消耗对比

Fig.10 Comparison of model synchronization time consumption under different bandwidth conditions

参考文献 28

1	董祥千, 郭兵, 沈艳, 等. 一种高效安全的去中心化数据共享模型. 计算机学报, 2018, 41(5): 1021- 1036. URL
	DONG X Q, GUO B, SHEN Y, et al. An efficient and secure decentralizing data sharing model. Chinese Journal of Computers, 2018, 41(5): 1021- 1036. URL
2	周全兴, 李秋贤, 丁红发, 等. 基于博弈论优化的高效联邦学习方案. 计算机工程, 2022, 48(8): 144-151, 159. URL
	ZHOU Q X, LI Q X, DING H F, et al. Efficient federated learning scheme based on game theory optimization. Computer Engineering, 2022, 48(8): 144-151, 159. URL
3	ZHAN Y F, LI P, GUO S, et al. Incentive mechanism design for federated learning: challenges and opportunities. IEEE Network, 2021, 35(4): 310- 317. doi: 10.1109/MNET.011.2000627
4	MCMAHAN H B, MOORE E, RAMAGE D, et al. Communication-efficient learning of deep networks from decentralized data[C]//Proceedings of the 20th International Conference on Artificial Intelligence and Statistics. [S. l. ]: PMLR, 2017: 1273-1282.
5	WANG L P, WANG W, LI B. CMFL: mitigating communication overhead for federated learning[C]//Proceedings of the 39th International Conference on Distributed Computing Systems. Washington D. C., USA: IEEE Press, 2019: 954-964.
6	NIKNAM S, DHILLON H S, REED J H. Federated learning for wireless communications: motivation, opportunities, and challenges. IEEE Communications Magazine, 2020, 58(6): 46- 51. doi: 10.1109/MCOM.001.1900461
7	ZHAN Y F, LI P, QU Z H, et al. A learning-based incentive mechanism for federated learning. IEEE Internet of Things Journal, 2020, 7(7): 6360- 6368. doi: 10.1109/JIOT.2020.2967772
8	WANG G, DANG C X, ZHOU Z Y. Measure contribution of participants in federated learning[C]//Proceedings of International Conference on Big Data. Washington D. C., USA: IEEE Press, 2019: 2597-2604.
9	陈乃月, 金一, 李浥东, 等. 基于区块链的公平性联邦学习模型. 计算机工程, 2022, 48(6): 33- 41. URL
	CHEN N Y, JIN Y, LI Y D, et al. Federated learning model with fairness based on blockchain. Computer Engineering, 2022, 48(6): 33- 41. URL
10	KIM H, PARK J, BENNIS M, et al. Blockchained on-device federated learning. IEEE Communications Letters, 2020, 24(6): 1279- 1283. doi: 10.1109/LCOMM.2019.2921755
11	TOYODA K, ZHANG A N. Mechanism design for an incentive-aware blockchain-enabled federated learning platform[C]//Proceedings of International Conference on Big Data. Washington D. C., USA: IEEE Press, 2019: 395-403.
12	王鑫, 周泽宝, 余芸, 等. 一种面向电能量数据的联邦学习可靠性激励机制. 计算机科学, 2022, 49(3): 31- 38. URL
	WANG X, ZHOU Z B, YU Y, et al. Reliable incentive mechanism for federated learning of electric metering data. Computer Science, 2022, 49(3): 31- 38. URL
13	张沁楠, 朱建明, 高胜, 等. 基于区块链和贝叶斯博弈的联邦学习激励机制. 中国科学(信息科学), 2022, 52(6): 971- 991. URL
	ZHANG Q N, ZHU J M, GAO S, et al. Incentive mechanism for federated learning based on blockchain and Bayesian game. Scientia Sinica (Informationis), 2022, 52(6): 971- 991. URL
14	LV H T, ZHENG Z Z, LUO T, et al. Data-free evaluation of user contributions in federated learning[C]//Proceedings of the 19th International Symposium on Modeling and Optimization in Mobile, Ad hoc, and Wireless Networks. Washington D. C., USA: IEEE Press, 2021: 1-8.
15	XUAN S C, JIN M, LI X, et al. DAM-SE: a blockchain-based optimized solution for the counterattacks in the Internet of federated learning systems[EB/OL]. [2023-02-01]. http://www.hindawi.com/journals/scn/2021/9965157.
16	LI Y Z, CHEN C, LIU N, et al. A blockchain-based decentralized federated learning framework with committee consensus. IEEE Network: the Magazine of Global Internetworking, 2021, 35(1): 234- 241. doi: 10.1109/MNET.011.2000263
17	LU Y L, HUANG X H, DAI Y Y, et al. Blockchain and federated learning for privacy-preserved data sharing in industrial IoT. IEEE Transactions on Industrial Informatics, 2020, 16(6): 4177- 4186. doi: 10.1109/TII.2019.2942190
18	WAINAKH A, GUINEA A S, GRUBE T, et al. Enhancing privacy via hierarchical federated learning[C]//Proceedings of European Symposium on Security and Privacy Workshops. Washington D. C., USA: IEEE Press, 2020: 344-347.
19	HEGEDŰS I, DANNER G, JELASITY M. Gossip learning as a decentralized alternative to federated learning[C]//Proceedings of International Conference on Distributed Applications and Interoperable Systems. Berlin, Germany: Springer, 2019: 74-90.
20	DENG Y H, LYU F, REN J, et al. SHARE: shaping data distribution at edge for communication-efficient hierarchical federated learning[C]//Proceedings of the 41st International Conference on Distributed Computing Systems. Washington D. C., USA: IEEE Press, 2021: 24-34.
21	JIANG J Y, HU L, HU C H, et al. BACombo—bandwidth-aware decentralized federated learning. Electronics, 2020, 9(3): 440. doi: 10.3390/electronics9030440
22	张学旺, 殷梓杰, 冯家琦, 等. 基于区块链与可信计算的数据交易方案. 计算机应用, 2021, 41(4): 939- 944. URL
	ZHANG X W, YIN Z J, FENG J Q, et al. Data trading scheme based on blockchain and trusted computing. Journal of Computer Applications, 2021, 41(4): 939- 944. URL
23	LIU Y, AI Z P, SUN S, et al. FedCoin: a peer-to-peer payment system for federated learning[M]//YANG Q, FAN L, YU H. Federated learning. Berlin, Germany: Springer, 2020: 125-138.
24	DAI W Q, DAI C K, CHOO K K R, et al. SDTE: a secure blockchain-based data trading ecosystem. IEEE Transactions on Information Forensics and Security, 2020, 15, 725- 737. doi: 10.1109/TIFS.2019.2928256
25	ANATI I, GUERON S, JOHNSON S, et al. Innovative technology for CPU based attestation and sealing[C]//Proceedings of the 2nd International Workshop on Hardware and Architectural Support for Security and Privacy. New York, USA: ACM Press, 2013: 1-7.
26	SONG T S, TONG Y X, WEI S Y. Profit allocation for federated learning[C]//Proceedings of International Conference on Big Data. Washington D. C., USA: IEEE Press, 2019: 2577-2586.
27	LI T, SAHU A K, TALWALKAR A, et al. Federated learning: challenges, methods, and future directions. IEEE Signal Processing Magazine, 2020, 37(3): 50- 60. doi: 10.1109/MSP.2020.2975749
28	ZHANG C, XIE Y, BAI H, et al. A survey on federated learning. Knowledge-Based Systems, 2021, 216, 106775. doi: 10.1016/j.knosys.2021.106775

[1]	李宝莹, 李志淮, 王成爱, 杨锋. 自适应节点规模的区块链分片可扩展模型[J]. 计算机工程, 2024, 50(3): 137-147.
[2]	宋华伟, 李升起, 万方杰, 卫玉萍. 非独立同分布场景下的联邦学习优化方法[J]. 计算机工程, 2024, 50(3): 166-172.
[3]	张晓均, 李兴鹏, 唐伟, 郝云溥, 薛婧婷. 云-边融合的可验证隐私保护跨域联邦学习方案[J]. 计算机工程, 2024, 50(3): 148-155.
[4]	陈纪成, 包子健, 罗敏, 何德彪. 一种面向工业物联网的远程安全指令控制方案[J]. 计算机工程, 2024, 50(3): 28-35.
[5]	郑晨俊, 曾艳, 袁俊峰, 张纪林, 王鑫, 韩猛. 基于联邦学习的船舶AIS轨迹预测算法[J]. 计算机工程, 2024, 50(2): 298-307.
[6]	倪雪莉, 马卓, 王群. 区块链矿池网络及典型攻击方式综述[J]. 计算机工程, 2024, 50(1): 17-29.
[7]	蔡梓越, 谭北海, 余荣, 黄旭民, 王思明. 面向6G物联网设备协同的区块链动态分片[J]. 计算机工程, 2024, 50(1): 50-59.
[8]	崔怀勇, 张绍华, 李超, 戴炳荣. 一种基于Schnorr签名的区块链预言机改进方案[J]. 计算机工程, 2024, 50(1): 166-173.
[9]	刘阳, 张圣杰. 一种基于时间自动机的安全智能合约生成方法[J]. 计算机工程, 2023, 49(9): 137-143, 157.
[10]	张攀峰, 吴丹华, 董明刚. 基于粒子群优化的差分隐私深度学习模型[J]. 计算机工程, 2023, 49(9): 144-157.
[11]	王群, 李馥娟, 倪雪莉, 夏玲玲, 梁广俊. 区块链数据形成与隐私威胁[J]. 计算机工程, 2023, 49(8): 1-12.
[12]	郑美光, 杨泳. 基于互信息软聚类的个性化联邦学习算法[J]. 计算机工程, 2023, 49(8): 20-28.
[13]	陈福安, 柳毅. 基于区块链的V2G无证书环签密隐私保护方案[J]. 计算机工程, 2023, 49(6): 34-41,52.
[14]	温依霖, 赵乃良, 曾艳, 韩猛, 岳鲁鹏, 张纪林. 基于本地模型质量的客户端选择方法[J]. 计算机工程, 2023, 49(6): 131-143.
[15]	潘雪, 袁凌云, 黄敏敏. 基于区块链和域信任度的物联网跨域信任评估模型[J]. 计算机工程, 2023, 49(5): 181-190.

选择文件类型/文献管理软件名称

选择包含的内容