Orchestrating Blockchain with Decentralized Federated Learning in Edge Networks
Orchestrating Blockchain with Decentralized Federated Learning in Edge Networks
复制标题
DOI：
10.1109/secon58729.2023.10287416
复制
发表时间：
2023-09
期刊：
影响因子：
--
通讯作者：
Yibo Jin;Lei Jiao;Zhuzhong Qian;Ruiting Zhou;Lingjun Pu
中科院分区：
文献类型：
--
作者：
Yibo Jin;Lei Jiao;Zhuzhong Qian;Ruiting Zhou;Lingjun Pu
跨边缘网络的分散式联邦学习可以利用具有共识机制的区块链，在昂贵且不信任的广域网上培训参与者之间的信息交换。然而，由于区块链操作的复杂成本结构、区块链开销和模型收敛之间的平衡以及边缘网络环境的动态性和不确定性，优化区块链以支持分散式联邦学习并非易事。为了克服这些挑战，我们制定了一个非线性时变整数规划，该规划联合放置区块链节点并确定训练迭代次数，以最大限度地减少长期区块链计算和通信成本。然后，我们设计了一个在线多项式时间近似算法，分解的问题，并解决了子问题交替使用估计的输入。我们严格证明了我们的方法的次线性遗憾。我们进一步实现我们的方法与原型系统，并进行广泛的跟踪驱动的实验，以验证我们的方法比其他替代品的优越性。
Decentralized federated learning across edge networks can leverage blockchain with consensus mechanisms for training information exchange among participants over costly and distrustful wide-area networks. However, it is non-trivial to optimally operate the blockchain to support decentralized federated learning due to the complex cost structure of blockchain operations, the balance between blockchain overhead and model convergence, and the dynamics and uncertainties of edge network environments. To overcome these challenges, we formulate a non-linear time-varying integer program that jointly places blockchain nodes and determines the number of training iterations to minimize the long-term blockchain computation and communication cost. We then design an online polynomial-time approximation algorithm that decomposes the problem and solves the subproblems alternately on the fly using only estimated inputs. We rigorously prove the sublinear regret of our approach. We further implement our approach with a prototype system, and conduct extensive trace-driven experiments to validate the superiority of our approach over other alternatives.