LF3PFL: A Practical Privacy-Preserving Federated Learning Algorithm Based on Local Federalization Scheme.

In the realm of federated learning (FL), the exchange of model data may inadvertently expose sensitive information of participants, leading to significant privacy concerns. Existing FL privacy-preserving techniques, such as differential privacy (DP) and secure multi-party computing (SMC), though offering viable solutions, face practical challenges including reduced performance and complex implementations. To overcome these hurdles, we propose a novel and pragmatic approach to privacy preservation in FL by employing localized federated updates (LF3PFL) aimed at enhancing the protection of participant data. Furthermore, this research refines the approach by incorporating cross-entropy optimization, carefully fine-tuning measurement, and improving information loss during the model training phase to enhance both model efficacy and data confidentiality. Our approach is theoretically supported and empirically validated through extensive simulations on three public datasets: CIFAR-10, Shakespeare, and MNIST. We evaluate its effectiveness by comparing training accuracy and privacy protection against state-of-the-art techniques. Our experiments, which involve five distinct local models (Simple-CNN, ModerateCNN, Lenet, VGG9, and Resnet18), provide a comprehensive assessment across a variety of scenarios. The results clearly demonstrate that LF3PFL not only maintains competitive training accuracies but also significantly improves privacy preservation, surpassing existing methods in practical applications. This balance between privacy and performance underscores the potential of localized federated updates as a key component in future FL privacy strategies, offering a scalable and effective solution to one of the most pressing challenges in FL.

An Optimization Method for Non-IID Federated Learning Based on Deep Reinforcement Learning.

Federated learning (FL) is a distributed machine learning paradigm that enables a large number of clients to collaboratively train models without sharing data. However, when the private dataset between clients is not independent and identically distributed (non-IID), the local training objective is inconsistent with the global training objective, which possibly causes the convergence speed of FL to slow down, or even not converge. In this paper, we design a novel FL framework based on deep reinforcement learning (DRL), named FedRLCS. In FedRLCS, we primarily improved the greedy strategy and action space of the double DQN (DDQN) algorithm, enabling the server to select the optimal subset of clients from a non-IID dataset to participate in training, thereby accelerating model convergence and reaching the target accuracy in fewer communication epochs. In simulation experiments, we partition multiple datasets with different strategies to simulate non-IID on local clients. We adopt four models (LeNet-5, MobileNetV2, ResNet-18, ResNet-34) on the four datasets (CIFAR-10, CIFAR-100, NICO, Tiny ImageNet), respectively, and conduct comparative experiments with five state-of-the-art non-IID FL methods. Experimental results show that FedRLCS reduces the number of communication rounds required by 10-70% with the same target accuracy without increasing the computation and storage costs for all clients.