While semi-asynchronous federated learning (SAFL) combines the efficiency of synchronous training with the flexibility of asynchronous updates, it inherently suffers from participation bias, which is further exacerbated by non-IID data distributions. More importantly, hierarchical architecture shifts participation from individual clients to client groups, thereby further intensifying this issue. Despite notable advancements in SAFL research, most existing works still focus on conventional cloud-end architectures while largely overlooking the critical impact of non-IID data on scheduling across the cloud–edge–client hierarchy. To tackle these challenges, we propose FedCure, an innovative semiasynchronous Federated learning framework that leverages Coalition construction and participation-aware scheduling to mitigate participation bias with non-IID data. Specifically, FedCure operates through three key rules: (1) a preference rule that optimizes coalition formation by maximizing collective benefits and establishing theoretically stable partitions to reduce non-IID-induced performance degradation; (2) a scheduling rule that integrates the virtual queue technique with Bayesian-estimated coalition dynamics, mitigating efficiency loss while ensuring mean rate stability; and (3) a resource allocation rule that enhances computational efficiency by optimizing client CPU frequencies based on estimated coalition dynamics while satisfying delay requirements. Comprehensive experiments on four real-world datasets demonstrate that FedCure improves accuracy by up to 5.1x compared with four state-of-the-art baselines, while significantly enhancing efficiency with the lowest coefficient of variation 0.0223 for per-round latency and maintaining long-term balance across diverse scenarios.

Asynchronous Federated Learning (AFL) is acclaimed for accelerating collaborative training on heterogeneous systems by eliminating the wait for stragglers. While current solutions focus on improving convergence amidst update delays, they neglect how delayed aggregation fosters free-riding attacks, allowing malicious clients to easily extract the global model without contribution. This behavior results in significant fairness issues and performance degradation. To address this challenge, we propose OPTION, the first online pricing strategy tailored to mitigate free-riding in AFL. OPTION establishes an economic model in which access to model updates is purchased using credits earned from verified contributions. Specifically, OPTION values each model update according to its marginal performance gain and training cost, and subsequently necessitates a download fee from each client based on the Hotelling model to prevent zero-cost acquisition. Moreover, OPTION rewards clients for successful updates under non-arbitrage constraints, effectively balancing individual utility and task budget. To maximize the average model performance while satisfying these conditions, OPTION leverages the Lyapunov drift framework and a probabilistic sampling-based algorithm to optimize the pricing parameters. Extensive experimental results on three real-world datasets demonstrate that OPTION effectively mitigates freeriding attacks in AFL, increases the number of valid updates by at least 23.97%, and achieves a model accuracy improvement of at least 3.01% compared to state-of-the-art baselines.

With the increasing application of high-stakes decisionmaking application in Federated Learning (FL), ensuring fairness across different populations to prevent biases against certain groups has become crucial. However, achieving group fairness (GF) in FL presents a formidable challenge due to its decentralization, which complicates the global GF estimation by the server. Moreover, distrust and fragility hinder the server from gathering GF values from unreliable clients. This challenge motivates our proposal of OursFed, a provable GF-aware FL framework that integrates a privacy pairbased contract and robust GF estimation method to address issues of distrust and fragility. Methodologically, we categorize client unreliability into two categories: active unreliability stemming from distrust and passive unreliability arising from fragility. To mitigate active unreliability, we design a privacy pair-based contract to guarantee truthful GF reporting, and enhance multivariate analysis by identifying relationships among multiple private data. To counteract passive unreliability, we develop a robust GF estimation using non-parametric techniques to smooth data and estimate probability densities and regression functions, improving per-client GF accuracy under multi-dimensional data perturbation. Theoretically, we demonstrate the efficacy of OursFed by analyzing its convergence, GF stability, and accuracy deviation. Experimentally, evaluations on two real datasets show that OursFed improves GF by 28.61% with at most 2.7% trade-off versus state-ofthe-art baselines, and synthetic experiments further confirm its effectiveness in handling fragility and distrust.

Federated Learning (FL) has gained widespread attention because it doesn’t require users to share their private data. However, since sensitive information can still be inferred from the uploaded models by users, Differential Privacy (DP) is often employed to safeguard these submitted models. Existing work mainly focused on uniformly allocating privacy budget to each layer of submitted models, which can lead to performance degradation, such as slower convergence rates and reduced generalization capabilities of the global model. To address this issue, this paper proposes a novel Differential Privacy Federated Learning framework, called Personalized Layer Privacy Protection Federated Learning Based on Mutual Information (MIPP-FL). In MIPP-FL, we first calculate the entropies of each layer’s weights of local models to establish a distribution of weights for each training round. Based on the entropies, the mutual information between current and last training rounds can be further obtained. Finally, for a given local model, we dynamically allocate the privacy budget to each layer by considering the calculated mutual information. Theoretically, we have demonstrated that the proposed MIPP-FL framework ensures strict privacy guarantee. Moreover, extensive experiments have shown that our proposed method can improve accuracy and achieve a faster convergence rate than the existing method that allocated the same privacy budgets uniformly to all layers of a local model.

In computer multimedia, Federated Learning (FL) enables clients to contribute their multimedia data, thereby improving the overall accuracy of the model. However, clients’ sensitive multimedia data could still be inferred through the submitted local models in FL. As a result, differential privacy (DP) techniques have been adopted to protect clients’ sensitive multimedia data. But existing works primarily focused on adding fixed noise to data, gradients, or loss functions, which can negatively affect the model’s accuracy and convergence. To address this issue, we propose a novel differential privacy federated learning framework (DP-FedAR) which consists of two modules, i.e., an adaptive budget allocation method and a reversion mechanism. Specifically, based on model similarity, an adaptive allocation rule is proposed to assign privacy budgets in real time for each training round. Then, in order to avoid exhausting the privacy budget of each client too early in the whole training process, a reversion mechanism is further devised to identify clients’ historical models that mostly resemble the current global model. Theoretical analyses demonstrate that our proposed DP-FedAR can converge and has a strict privacy guarantee. Moreover, extensive simulations validate that our proposed DP-FedAR outperforms existing algorithms in terms of training accuracy. More precisely, the accuracy of DP-FedAR surpasses that of counterparts, with an average improvement of 8% to 12%

Online Federated Learning (OFL) is a real-time learning paradigm that sequentially executes parameter aggregation immediately for each random arriving client. To motivate clients to participate in OFL, it is crucial to offer appropriate incentives to offset the training resource consumption. However, the design of incentive mechanisms in OFL is constrained by the dynamic variability of Two-sided Incomplete Information (TII) concerning resources, where the server is unaware of the clients’ dynamically changing computational resources, while clients lack knowledge of the real-time communication resources allocated by the server. To incentivize clients to participate in training by offering dynamic rewards to each arriving client, we design a novel Dynamic Bayesian persuasion pricing for online Federated learning (DaringFed) under TII. Specifically, we begin by formulating the interaction between the server and clients as a dynamic signaling and pricing allocation problem within a Bayesian persuasion game, and then demonstrate the existence of a unique Bayesian persuasion Nash equilibrium. By deriving the optimal design of DaringFed under one-sided incomplete information, we further analyze the approximate optimal design of DaringFed with a specific bound under TII. Finally, extensive evaluation conducted on real datasets demonstrate that DaringFed optimizes accuracy and converges speed by 16.99%, while experiments with synthetic datasets validate the convergence of estimate unknown values and the effectiveness of DaringFed in improving the server’s utility by up to 12.6%.

Semi-Asynchronous Federated Learning (SAFL) leverages the benefits of synchronous and asynchronous updates, effectively addressing the straggling effect caused by heterogeneity among clients. However, most research focuses on synchronous FL, overlooking the incentive mechanisms crucial for active participation in SAFL. Moreover, client-specific private information including data quality, computational resources, and privacy preferences is multi-dimensional and inaccessible to the server, yet essential for effective decision-making. To address these challenges, we propose a novel SAFL framework incorporating a learning-based contract with the consideration of multi-dimensional private information. Specifically, we integrate model staleness and data quality into the aggregated weight design in the proposed SAFL. Then, we formulate a server utility maximization problem to optimize local iterations and reward allocation for different client types, ensuring theoretical guarantees of convergence, individual rationality (IR), and incentive compatibility (IC). Extensive simulations on real-world datasets demonstrate that our approach significantly enhances global accuracy and convergence speed compared to existing works on aggregation and contract design methods.

In the operational context of a cross-device federated learning (FL), the efficient allocation of resources, such as transmission powers, channels, and computation resources, significantly impacts overall performance. Existing research in cross-device FL has predominantly concentrated on either resource allocation to enhance training accuracy or incentivizing participation, while ignoring their integrated designs for further improving the performance in cross-device FL. Different from existing work, in this paper, we jointly integrate the power allocation, channel assignment, user selection, and allocation of computation frequency into the design of incentive mechanism, where each mobile user plays a dual role as both a buyer and a seller. Because of complex resource allocation, truthfulness guarantee in a dual role scenario, and unavailable prior information, the considered mechanism design problem is challenging. To tackle such combinatorial problem, we propose a Reinforcement Auction Mechanism (RAM), comprising two layers. The upper layer features a Hybrid Action Reinforcement Learning scheme to learn the outcomes of user selection and payments. In the lower layer, each selected mobile user optimizes its resources to maximize its utility. Theoretical analyses affirm that our proposed RAM ensures individual rationality and truthfulness. Extensive simulations have been conducted to validate the effectiveness of the proposed RAM.

In this article, we consider incentive mechanism designs in asynchronous federated learning (FL) systems. With the consideration of unique characteristics inherent in asynchronous FL, such as dynamic participating and multiminded IoT nodes such as mobile users (MUs), requirements of model training (i.e., training accuracy and convergence time), and limited uplink bandwidth, we formulate considered system as an online incentive mechanism design problem, where each MU is not only a buyer for communication resource but also a seller for computation service. To address the challenges involved in the design, we first derive the relationship between the number of participants and the global training accuracy in asynchronous FL. Then, based on that, we propose a novel mechanism, called the online incentive mechanism for asynchronous FL (OIMAF). To the best of our knowledge, this is the first work to design incentive mechanisms for asynchronous FL. Furthermore, in order to obtain a more robust mechanism, an improved online mechanism, called the two-shot-based online incentive mechanism (TOIM), is proposed by using OIMAF as a building block. Theoretical analyses show that our proposed online incentive mechanisms can guarantee individual rationality, truthfulness, a sound performance, and solution feasibilities. We further conduct comprehensive simulations to validate the effectiveness of our proposed mechanisms.

In this paper, we consider task offloading in edge computing systems, where tasks are offloaded by the base station to resourceful mobile users. With the consideration of unique characteristics in practical edge computing systems, such as dynamic arrival of computation tasks, and energy constraints at battery-powered mobile users, we formulate an incentive mechanism design problem by jointly optimizing task offloading decisions, and allocation of both communications (i.e., power and bandwidth), and computation resources. In order to tackle the nonlinear issue in the designed mechanism, a novel online incentive mechanism is proposed. We first convert the original mechanism design problem into several one-shot design problems by temporally removing the energy constraint. Then, we propose a new mechanism design framework, called the Integrate Rounding Scheme based Maxima-in-distributional Range (IRSM), and based on that, design a new incentive mechanism for each one-shot problem. Finally, we reconsider energy constraints to design a new nonlinear online incentive mechanism by rationally combining the previously derived one-shot ones. Theoretical analyses show that our proposed nonlinear online incentive mechanism can guarantee individual rationality, truthfulness, a sound competitive ratio, and computational efficiency. We further conduct comprehensive simulations to validate the effectiveness and superiority of our proposed mechanism.

In this article, an online truthful mechanism is designed for mobile crowdsensing systems. Traditionally, the scenario where participants arrived at the platform in an online manner has been widely discussed in existing works. On the contrary, we focus on random task arrival case to design an online truthful mechanism by jointly considering the cost budget and the requirement of sensed data of each participant. Specifically, when the task arrives, the platform must make decisions in a sequence to select a specific number of participants to obtain a better competitive ratio (CR). To address this issue, an online strategy-proof incentive mechanism is designed to minimize the social cost of the whole system and achieve truthfulness by applying the auction framework. Moreover, in order to further improve the CR of the online algorithm, a more efficient online scheme is proposed if more information on the participants is available at the platform. Theoretical and simulation results demonstrate the effectiveness of our proposed online truthful mechanisms.

This paper discusses incentive mechanism design for collaborative task offloading in mobile edge computing (MEC). Different from most existing work in the literature that was based on offline settings, in this paper, an online truthful mechanism integrating computation and communication resource allocation is proposed. In our system model, upon the arrival of a smartphone user who requests task offloading, the base station (BS) needs to make a decision right away without knowing any future information on i) whether to accept or reject this task offloading request and ii) if accepted, who to execute the task (the BS itself or nearby smartphone users called collaborators). By considering each task's specific requirements in terms of data size, delay, and preference, we formulate a social-welfare-maximization problem, which integrates collaborator selection, communication and computation resource allocation, transmission and computation time scheduling, as well as pricing policy design. To solve this complicated problem, a novel online mechanism is proposed based on the primal-dual optimization framework. Theoretical analyses show that our mechanism can guarantee feasibility, truthfulness, and computational efficiency (competitive ratio of 3). We further use comprehensive simulations to validate our analyses and the properties of our proposed mechanism.

In this paper, an online truthful mechanism integrating task executor selection, computation and communication resource allocation is proposed. Different from most existing work in the literature that was based on offline settings, in our system model, upon the arrival of a smartphone user who requests task offloading, the base station (BS) needs to make a decision right away without knowing any future information. By considering each task's specific requirements in terms of data size, delay, and preference, we formulate a social-welfare-maximization problem and propose a novel online mechanism to solve it. Both theoretical analyses and numerical results show that our mechanism can guarantee feasibility, truthfulness, and computational efficiency with a competitive ratio of 3.

In this paper, an online incentive mechanism in crowdsensing systems is studied. Different from most of the existing works which considered the smartphone users arriving at the crowdsourcer in an online fashion, we concentrate on the uncertain task arrivals, and consider the smartphone user allocation problem by jointly taking the cost capacity of each smartphone user and the sensing data quality requirement into consideration. In our model, since the tasks arrive at the crowdsourcer in an online manner, the crowdsourcer must make decisions timely to choose a suitable subset of smartphone users to achieve a sound competitive ratio (compared to the offline solution) once the tasks arrive. For the purpose of minimizing social cost in the whole system and achieving truthfulness, an online strategy proof incentive mechanism is designed by applying randomized auction framework. Theoretical and simulation results verify the effectiveness of the proposed online incentive mechanism.