【Author】
Huang, Xiaoge; Zhi, Chen; Chen, Qianbin; Zhang, Jie
【Source】2021 IEEE 94TH VEHICULAR TECHNOLOGY CONFERENCE (VTC2021-FALL)
【Abstract】In mobile computing scenarios, federation learning allows users to jointly train global models in a decentralized manner without exposing private data. However, due to the heterogeneity of the network and devices, the traditional global model often fails to fit the user data distribution, which is inconsistent with the primary condition of federation learning, resulting in accuracy decreasing of global models. Besides, the security of federated learning is decreasing with the increase of malicious attacks. To address the aforementioned issues, in this paper, we explore the cosine similarity of model gradients and design a clustered mechanism to improve learning efficiency. Furthermore, we combine the clustered federated learning with the blockchain-supported fog computing networks, which could verify local models uploaded by users and generate the traceable global models to improve the learning efficiency. Finally, we conduct experiments on several frameworks with the real-world dataset FEMNIST, and the experimental results demonstrate the efficiency and robustness of the blockchain-enabled clustered federated learning framework.
【Keywords】Fog computing networks; Federated learning; Clustering; Blockchain
【摘要】在移动计算场景中，联邦学习允许用户以去中心化的方式联合训练全局模型，而不会暴露私有数据。然而，由于网络和设备的异构性，传统的全局模型往往无法拟合用户数据分布，这与联邦学习的主要条件不符，导致全局模型精度下降。此外，联邦学习的安全性随着恶意攻击的增加而降低。针对上述问题，本文探讨了模型梯度的余弦相似度，并设计了一种聚类机制来提高学习效率。此外，我们将集群联邦学习与区块链支持的雾计算网络相结合，可以验证用户上传的本地模型并生成可追溯的全局模型，以提高学习效率。最后，我们使用真实世界的数据集 FEMNIST 对几个框架进行了实验，实验结果证明了支持区块链的集群联邦学习框架的效率和鲁棒性。
评论