As a distributed learning approach, federated learning trains a shared learning model over distributed datasets while preserving the training data privacy. We extend the application of federated learning to parking management and introduce FedParking in which Parking Lot Operators (PLOs) collaborate to train a long short-term memory model for parking space estimation without exchanging the raw data. Furthermore, we investigate the management of Parked Vehicle assisted Edge Computing (PVEC) by FedParking. In PVEC, different PLOs recruit PVs as edge computing nodes for offloading services through an incentive mechanism, which is designed according to the computation demand and parking capacity constraints derived from FedParking. We formulate the interactions among the PLOs and vehicles as a multi-lead multi-follower Stackelberg game. Considering the dynamic arrivals of the vehicles and time-varying parking capacity constraints, we present a multi-agent deep reinforcement learning approach to gradually reach the Stackelberg equilibrium in a distributed yet privacy-preserving manner. Finally, numerical results are provided to demonstrate the effectiveness and efficiency of our scheme.

Artificial intelligence generated content (AIGC) has emerged as a promising technology to improve the efficiency, quality, diversity and flexibility of the content creation process by adopting a variety of generative AI models. Deploying AIGC services in wireless networks has been expected to enhance the user experience. However, the existing AIGC service provision suffers from several limitations, e.g., the centralized training in the pre-training, fine-tuning, and inference processes, especially their implementations in wireless networks with privacy preservation. Federated learning (FL), as a collaborative learning framework where the model training is distributed to cooperative data owners without the need for data sharing, can be leveraged to simultaneously improve learning efficiency and achieve privacy protection for AIGC. To this end, we present FL-based techniques for empowering AIGC, and aim to enable users to generate diverse, personalized, and high-quality content. Furthermore, we conduct a case study of FL-aided AIGC fine-tuning by using the state-of-the-art AIGC model, i.e., stable diffusion model. Numerical results show that our scheme achieves advantages in effectively reducing the communication cost and training latency, and providing privacy protection. Finally, we highlight several major research directions and open issues for the convergence of FL and AIGC.

Distributed Artificial Intelligence (AI) model training over mobile edge networks encounters significant challenges due to the data and resource heterogeneity of edge devices. The former hampers the convergence rate of the global model, while the latter diminishes the devices' resource utilization efficiency. In this paper, we propose a generative AI-empowered federated learning to address these challenges by leveraging the idea of FIlling the MIssing (FIMI) portion of local data. Specifically, FIMI can be considered as a resource-aware data augmentation method that effectively mitigates the data heterogeneity while ensuring efficient FL training. We first quantify the relationship between the training data amount and the learning performance. We then study the FIMI optimization problem with the objective of minimizing the device-side overall energy consumption subject to required learning performance constraints. The decomposition-based analysis and the cross-entropy searching method are leveraged to derive the solution, where each device is assigned suitable AI-synthetic data and resource utilization policy. Experiment results demonstrate that FIMI can save up to 50% of the device-side energy to achieve the target global test accuracy in comparison with the existing methods. Meanwhile, FIMI can significantly enhance the converged global accuracy under the non-independently-and-identically distribution (non-IID) data.

The smart ocean has been regarded as an integrated sensing, communication, and computing ecosystem developed for connecting marine objects in surface and underwater environments. The development of the smart ocean is expected to support a variety of marine applications and services such as resource exploration, marine disaster rescuing, and environment monitoring. However, the complex and dynamic marine environments and the limited network resources raise new challenges in marine communication and computing, especially for these computing-intensive and delay-sensitive tasks. Recently, the space–air–ground–sea integrated networks have been envisioned as a promising network framework to enhance the communication and computing performance. In this paper, we conduct a comprehensive survey on the integrated sensing, communication, and computing networks (ISCCNs) for smart oceans based on the collaboration of space–air–ground–sea networks from four domains (i.e., space layer, aerial layer, sea surface layer, and underwater layer), and five aspects (i.e., sensing-related, communication-related, computation-related, security-related, and application-related). Specifically, we provide the key technologies for the ISCCNs in smart oceans, and introduce the state-of-the-art marine sensing, communication, and computing paradigms. The emerging challenges with the potential solutions of the ISCCNs for smart oceans are illustrated to enable the intelligent services. Moreover, the new applications for the ISCCNs in smart oceans are discussed, and potential research directions in smart oceans are provided for future works.

As a key paradigm of future 6G networks, Space-Air-Ground Integrated Networks (SAGIN) has been envisioned to provide numerous intelligent applications that necessitate the cooperation of a multitude of terrestrial devices for machine learning (ML) model training. Utilizing the satellite as the central server, federated learning (FL) offers a promising strategy for distributed training with enhanced data security and privacy. However, employing FL in SAGIN faces challenges in managing vast datasets, training complicated ML models, and ensuring security in long-distance transmission of ML models. In this article, we propose a quantum-empowered FL framework integrating variational quantum algorithms (VQA) and quantum relays in SAGIN. Our approach employs VQA-based ML for local training of FL, addressing the complexity emerging from vast datasets and ML models. Furthermore, supported by unmanned aerial vehicles (UAVs) and high-altitude platform stations (HAPS), the proposed quantum relay scheme via quantum teleportation guarantees security in long-distance model transmission. We present a case study to validate the proposed VQA-based local training and quantum relaying model transmission. The numerical results demonstrate the feasibility and efficiency of the proposed VQA-based FL framework and the quantum relay-based model transmission. Our approach highlights the potential of integrating quantum techniques with FL in SAGIN, which can enable secure, efficient, and advanced edge intelligence applications.

Model update compression is a widely used technique to alleviate the communication cost in federated learning (FL). However, there is evidence indicating that the compression-based FL system often suffers the following two issues, i) the implicit learning performance deterioration of the global model due to the inaccurate update, ii) the limitation of sharing the same compression rate over heterogeneous edge devices. In this paper, we propose an energy-efficient learning framework, named Snowball, that enables edge devices to incrementally upload their model updates in a coarse-to-fine compression manner. To this end, we first design a fine-grained compression scheme that enables a nearly continuous compression rate. After that, we investigate the Snowball optimization problem to minimize the energy consumption of parameter transmission with learning performance constraints. By leveraging the theoretical insights of the convergence analysis, the optimization problem is transformed into a tractable form. Following that, a water-filling algorithm is designed to solve the problem, where each device is assigned a personalized compression rate according to the status of the locally available resource. Experiments indicate that, compared to state-of-the-art FL algorithms, our learning framework can save five times the required energy of uplink communication to achieve a good global accuracy.