基于多目标优化的联邦学习进化算法

传统联邦学习存在通信成本高、结构异构、隐私保护力度不足的问题，为此提出了一种联邦学习进化算法，应用稀疏进化训练算法降低通信成本，结合本地化差分隐私保护参与方隐私，同时采用NSGA-Ⅲ算法优化联邦学习全局模型的网络结构、稀疏性，调整数据可用性与隐私保护之间的关系，实现联邦学习全局模型有效性、通信成本和隐私性的均衡。不稳定通信环境下的实验结果表明，在MNIST和CIFAR-10数据集上，与FNSGA-Ⅲ算法错误率最低的解相比，该算法所得解的通信效率分别提高57.19%和52.17%，并且参与方实现了（3.46，10-4）和（6.52，10-4）-本地化差分隐私。在不严重影响全局模型准确率的前提下，该算法有效降低了联邦学习的通信成本并保护了参与方隐私。

Federated learning evolutionary algorithm based on multi-objective optimization

Traditional federated learning faces challenges such as high communication costs, structural heterogeneity, and insufficient privacy protection. To address these issues, this paper proposed a federated learning evolutionary algorithm that applied sparse evolutionary training algorithm to reduce communication costs and integrated local differential privacy protection for participants'' privacy. Additionally, it utilized the NSGA-Ⅲ algorithm to optimize the network structure and sparsity of the global federated learning model, adjusting the relationship between data availability and privacy protection. This achieved a balance between the effectiveness, communication costs, and privacy of the global federated learning model. Experimental results under unstable communication environments demonstrate that, on the MNIST and CIFAR-10 datasets, compared to the solution with the lowest error rate using the FNSGA-Ⅲ algorithm, the proposed algorithm improves communication efficiency by 57.19% and 52.17%, respectively. The participants also achieved(3.46, 10-4) and(6.52, 10-4) -local differential privacy. This algorithm can effectively reduce communication costs and protect participant privacy without significantly compromising the accuracy of the global model.