This paper presents a novel approach for wireless federated learning (WFL) that, for the first time, enables the aggregation of local models with mild to moderate errors under practical communication settings, which has to date been prevented by floating-point standards, e.g., IEEE binary32, and encryption. Specifically, we propose a new conversion from floating-point local models to fixed-point models on a layer basis, eliminating the need to transmit error-intolerant sign and exponent bits of floating-point numbers while accommodating variations in model layer widths and magnitudes. We also quantify how bit errors in the ciphertext affect the plaintext when symmetric encryption is employed for local model uploading, e.g., under Rayleigh, Rician, and Nakagami-m fading channels. Notably, these bit errors are leveraged to enhance the privacy of local models. We interpret the local model transmission process as a (λ, ϵ)-Rényi Differential Privacy (DP) mechanism, where bit errors induced by noisy channels, controlled via transmit powers, and exacerbated by decryption act as DP perturbations. Experiments show the superiority of the new WFL to the status quo with higher training accuracy and lower communication overhead.

The timely exchange of information among robots within a team is vital, but it can be constrained by limited wireless capacity. The inability to deliver information promptly can result in estimation errors that impact collaborative efforts among robots. In this paper, we propose a new metric termed Loss of Information Utility (LoIU) to quantify the freshness and utility of information critical for cooperation. The metric enables robots to prioritize information transmissions within bandwidth constraints. We also propose the estimation of LoIU using belief distributions and accordingly optimize both transmission schedule and resource allocation strategy for device-to-device transmissions to minimize the time-average LoIU within a robot team. A semi-decentralized Multi-Agent Deep Deterministic Policy Gradient framework is developed, where each robot functions as an actor responsible for scheduling transmissions among its collaborators while a central critic periodically evaluates and refines the actors in response to mobility and interference. Simulations validate the effectiveness of our approach, demonstrating an enhancement of information freshness and utility by 98%, compared to alternative methods.

Inherent communication noises have the potential to preserve privacy for wireless federated learning (WFL) but have been overlooked in digital communication systems predominantly using floating-point number standards,e.g., IEEE 754, for data storage and transmission. This is due to the potentially catastrophic consequences of bit errors in floating-point numbers,e.g., on the sign or exponent bits. This paper presents a novel channel-native bit-flipping differential privacy (DP) mechanism tailored for WFL, where transmit bits are randomly flipped and communication noises are leveraged, to collectively preserve the privacy of WFL in digital communication systems. The key idea is to interpret the bit perturbation at the transmitter and bit errors caused by communication noises as a bit-flipping DP process. This is achieved by designing a new floating-point-to-fixed-point conversion method that only transmits the bits in the fraction part of model parameters, hence eliminating the need for transmitting the sign and exponent bits and preventing the catastrophic consequence of bit errors. We analyze a new metric to measure the bit-level distance of the model parameters and prove that the proposed mechanism satisfies (λ, ϵ)-Rényi DP and does not violate the WFL convergence. Experiments validate privacy and convergence analysis of the proposed mechanism and demonstrate its superiority to the state-of-the-art Gaussian mechanisms that are channel-agnostic and add Gaussian noise for privacy protection.

Personalized federated learning (PFL) offers a solution to balancing personalization and generalization by conducting federated learning (FL) to guide personalized learning (PL). Little attention has been given to wireless PFL (WPFL), where privacy concerns arise. Performance fairness of PL models is another challenge resulting from communication bottlenecks in WPFL. This paper exploits quantization errors to enhance the privacy of WPFL and proposes a novel quantization-assisted Gaussian differential privacy (DP) mechanism. We analyze the convergence upper bounds of individual PL models by considering the impact of the mechanism (i.e., quantization errors and Gaussian DP noises) and imperfect communication channels on the FL of WPFL. By minimizing the maximum of the bounds, we design an optimal transmission scheduling strategy that yields min-max fairness for WPFL with OFDMA interfaces. This is achieved by revealing the nested structure of this problem to decouple it into subproblems solved sequentially for the client selection, channel allocation, and power control, and for the learning rates and PL-FL weighting coefficients. Experiments validate our analysis and demonstrate that our approach substantially outperforms alternative scheduling strategies by 87.08%, 16.21%, and 38.37% in accuracy, the maximum test loss of participating clients, and fairness (Jain's index), respectively

Smart manufacturing aims to support highly dynamic and flexible production processes where intelligent machines are expected to have the ability to complete quickly transition from old applications to new ones. Federated transfer learning is a promising solution that enables knowledge sharing in the above process to rapidly provide models required for new tasks. To achieve efficient transfer, the challenge lies in how to provide transferable and high-quality data for new tasks while preserving data privacy. In this paper, we propose a novel cross-application federated transfer learning framework based on collaborative generative adversarial networks named CPFTL-CGAN. Specifically, we innovatively propose a source domain selection scheme based on domain similarity, which aims to select the most optimal source domain among massive candidates for efficient knowledge sharing. Furthermore, a collaborative generative adversarial network has been designed to generate data similar to the source, which addresses the problem that private source domain data cannot be shared directly to the target domain and further enhances the quality of the generated data. Finally, domain adaptation based on generated data is performed on target clients. Extensive simulation results demonstrate that the proposed CPFTL-CGAN can effectively improve the learning efficiency and accuracy compared to single-device training locally, Fedavg and ACGAN-FTL.