The heterogeneity of local data and client performance, along with real-world system risks, is driving the evolution of federated learning (FL) towards personalized, model-heterogeneous, and decentralized approaches. However, due to the differing structures of heterogeneous models, it is hard to use them to identify clients with similar data distributions and further enhance the personalization of local models. Therefore, how to deal with data heterogeneity to obtain superior personalized local models for clients, while simultaneously addressing model heterogeneity and system risks is a challenging problem. In this paper, we propose a novel personalized FL framework with fine-gRained layEr aggregAtion andDecentralized cluStering (${\sf Reads}$), which integrates four key components: (1) deep mutual learning with privacy guarantee for model training and privacy preservation, (2) fine-grained layer similarity computation among heterogeneous model layers, (3) fully decentralized clustering for soft clustering of clients based on layer similarities, and (4) personalized layer aggregation for capturing common knowledge from other clients. Through${\sf Reads}$, clients obtain personalized models that accommodate model heterogeneity, while the system ensures robustness against a single point of failure. Extensive experiments demonstrate the efficacy of${\sf Reads}$in achieving these goals.

The pervasive distribution of data across clients with privacy concerns and heterogeneous performance in edge networks presents a significant opportunity to enhance AI model performance. Federated learning (FL) enables a model owner (MO) to recruit these clients, offering compensation for their contributions, and to improve model quality by aggregating knowledge from their locally trained models. However, several challenges arise in this process. Clients may decline participation if they do not achieve positive utility. Moreover, due to constraints in memory, computing, and communication resources, some clients can only train lightweight models that represent partial versions of the global model. Importantly, the MO's pricing for client contributions and the proportions of local model training are interdependent, collectively influencing client utilities and participation decisions. To address these challenges, we first model the utility functions of both the MO and the clients, accommodating the support for lightweight local models. We then formulate their interactions as a Stackelberg game and theoretically prove the existence of a Nash equilibrium. Based on this equilibrium, we derive optimal collaboration strategies for both the MO and the clients. Additionally, we design an efficient approximation algorithm to enable the MO to maximize its utility by selecting suitable clients to participate in FL. Finally, extensive experiments validate our theoretical findings, demonstrating the superior performance and effectiveness of the proposed algorithms

Mobile edge computing (MEC) brings abundant computing resources to the edge networks, which supports users in offloading their tasks to the edge instead of the cloud, thereby reducing service delay and improving users' quality of experience. In this paper, we consider a three-tier multi-user multi-task offloading model, which contains multiple users with each user possessing multiple tasks, multiple base stations (BSs) with edge servers and a remote cloud. Taking into account the selfishness of individuals in the MEC system, we respectively formulate optimization problems for users, BSs and the cloud. Users aim to make their offloading strategies to minimize their respective costs, while BSs and the cloud aim to make their computation resource allocation decisions to minimize their respective task completion delays. We model the interaction among these selfish individuals based on Stackelberg game, where users act as leaders and BSs and the cloud act as followers. By using backward induction, we prove the existence of Stackelberg Equilibrium (SE). We further propose a distributed algorithm that enables the system to reach the SE, which includes three user selection strategies for the BSs. The numerical results demonstrate the superiority of the proposed scheme compared with several approaches.

Bidirectional service function chain (BSFC) consists of multiple virtual network functions (VNFs). Through VNF deployment and link mapping, BSFCs can be embedded into resource-constrained mobile edge networks to provide low-latency network function services to users participating in interactive applications such as multi-player online games. Data from these users are routed through BSFCs to the edge node where the application is located for interaction and then returned to the users through the BSFCs, thus enabling synchronization among multiple users. However, the edge nodes or links have limited computing or bandwidth resources to serve only a fraction of users simultaneously. Therefore, the embedding decisions among different users can affect each other. In this paper, we propose a novel BSFC embedding strategy for interactive applications with the goal of minimizing computing and bandwidth resources while satisfying users' latency requirements. We first model the BSFC embedding problem as an integer nonlinear programming problem. Then, by closely examining the complexity of the problem, we propose a distributed algorithm based on game theory. We theoretically analyze the properties of the proposed algorithm and show that it can obtain a solution with a worst-case performance bound. Finally, extensive experiments show that the proposed algorithm outperforms several existing algorithms.

Federated learning (FL) is a distributed machine learning paradigm that can be organized in two layers. In the outer layer of users, there is a model interaction process between the task publisher and users, through which all parties obtain their respective utilities. However, these parties’ utilities are coupled, both depending on the training sample size and local iterations. In the inner layer of users, a user's multiple devices (e.g., computers and smart phones) can be used to jointly train local models efficiently. Yet, due to device heterogeneity, it is challenging for users to determine which devices to participate in local training and allocate how many computing and communication resources to minimize training costs. In this paper, we tackle this novel two-layer optimization problem by designing utility game and resource control strategies. In the outer layer, we model the relationship between the task publisher and users as a Stackelberg game and obtain the optimal solution for both parties by solving a unique Stackelberg equilibrium point; while in the inner layer, we formulate the optimization problem as a mixed integer nonlinear programming problem, which is decomposed into sub-problems and solved by devising resource control algorithm based on successive convex approximation. Finally, extensive experiments show that the proposed algorithms outperform baseline algorithms.

Mobile edge Industrial Internet of Things (MEIIoT) is composed of Industrial Internet of Things (IIoT) and mobile edge computing, which is currently a new type of IIoT. MEIIoT has the characteristics of large scale and strong dynamics (e.g., network topology or number of IIoT devices would change from time to time). The placement of virtualized network functions (VNFs) in MEIIoT refers to placing multiple network functions (e.g., motion analyzer and video processor) on edge nodes in a form of software instances, so that IIoT devices can flexibly obtain services of these VNFs. However, an edge node can only be placed a small number of VNFs, because of its limited storage and computing resources. Therefore, if an IIoT device requires multiple VNFs, it needs to transmit its data to access several edge nodes, which would cause high delay. How to optimally place all the VNFs on edge nodes in MEIIoT, so that the whole access delay for all IIoT devices that requiring VNFs is minimized, is a challenging problem. In this article, we design an online placement algorithm. First, we decompose a long-term VNFs optimization problem into a series of one-shot optimization problems. Second, we formulate these one-shot problems into integer nonlinear programming problems, and prove that they are NP-hard. To overcome this hardness, we then propose a heuristic algorithm. Finally, we carried out extensive experiments with real-world datasets to validate the efficacy of our proposed solution.

Mobile edge computing (MEC) has emerged as a promising computing paradigm that provides flexible and responsive local services for mobile user equipment at the network edge. Software instances for user equipment tasks are typically deployed as Virtualized Network Functions (VNFs) at resource-constrained edge nodes. Task data exchanged across the VNFs in serial can incur high task completion latency. It is therefore desirable to deploy certain VNFs in parallel. However, deciding where to deploy VNFs depends on which VNFs are parallel, and conversely, their deployment also affects their parallel execution. In this paper, for the first time, we jointly consider the parallelization and deployment strategies for VNFs at edge nodes. We closely examine the complexity of the joint optimization problem and introduce an Improved Service Function Graph (I-SFG) that reflects the coordination and dependency relations among the VNFs to provide parallel services for each piece of user equipment. We first propose an approach based on integer linear programming to find optimal solutions in small-scale scenarios and then present an effective solution through cascading I-SFG construction and VNF deployment approximation to solve large-scale problems. Theoretical analyses and experimental results show the superiority of our joint design and the proposed practical solution.