Privacy-Enhanced Decentralized Federated Learning at Dynamic Edge

Decentralized Federated Learning (DeFL) plays a critical role in improving effectiveness of training and has been proved to give great scope to the development of edge computing. However, on the one hand, inaccessibility of private data and excessively exploiting the data throughout the learning process have become a public concern, and on the other hand the connections between server-less edge devices are always varying due to the mobility of edge intelligent devices. To address the above issues, we propose a P rivacy- E nhanced - D ynamic - D ecentralized - F ederated - L earning algorithm called PED \rm ^{2} FL in a dynamic edge environment. We design the PED \rm ^{2} FL under the analog transmission scheme, where mobile edge devices transmit privacy preserving data simultaneously and accomplish efficient information aggregation with doubly-stochastic adjacent matrices. With thorough analysis, it can be demonstrated that PED \rm ^{2} FL satisfies (\epsilon ,\delta )-differential privacy while the per-device privacy budget decays exponentially with the number of the neighbors, which greatly improved the data utility compared to the fixed budget in the orthogonal transmission strategy. PED \rm ^{2} FL has the same convergence rate \mathcal {O}(\sqrt{\frac{1}{KN}}) as the non-private decentralized learning algorithm D-PSGD without enhanced privacy protection, where K and N are the total iterations and the number of nodes, respectively. Extensive experiments show that algorithm PED \rm ^{2} FL also performs well with real-world settings.