Training of large-scale models is both computationally intensive and often constrained by the availability of labeled data. Model merging offers a compelling alternative by directly integrating the weights of multiple source models without requiring additional data or extensive training. However, conventional model merging techniques, such as parameter averaging, often suffer from the unintended combination of non-generalizable features, especially when source models exhibit significant weight disparities. Comparatively, model ensembling generally provides more stable and superior performance that aggregates multiple models by averaging outputs. However, it incurs higher inference costs and increased storage requirements. While previous studies experimentally showed the similarities between model merging and ensembling, theoretical evidence and evaluation metrics remain lacking. To address this gap, we introduce Merging-ensembling loss (M-loss), a novel evaluation metric that quantifies the compatibility of merging source models using very limited unlabeled data. By measuring the discrepancy between parameter averaging and model ensembling at layer and node levels, M-loss facilitates more effective merging strategies. Specifically, M-loss serves both as a quantitative criterion of the theoretical feasibility of model merging, and a guide for parameter significance in model pruning. Our theoretical analysis and empirical evaluations demonstrate that incorporating M-loss into the merging process significantly improves the alignment between merged models and model ensembling, providing a scalable and efficient framework for accurate model consolidation.

Large Language Models (LLMs) increasingly leverage Federated Learning (FL) to utilize private, task-specific datasets for fine-tuning while preserving data privacy. However, while federated LLM frameworks effectively enable collaborative training without raw data sharing, they critically lack built-in mechanisms for regulatory compliance like GDPR’s right to be forgotten. Integrating private data heightens concerns over data quality and long-term governance, yet existing distributed training frameworks offer no principled way to selectively remove specific client contributions post-training. Due to distributed data silos, stringent privacy constraints, and the intricacies of interdependent model aggregation, federated LLM unlearning is significantly more complex than centralized LLM unlearning. To address this gap, we introduce Oblivionis, a lightweight learning and unlearning framework that enables clients to selectively remove specific private data during federated LLM training, enhancing trustworthiness and regulatory compliance. By unifying FL and unlearning as a dual optimization objective, we incorporate 6 FL and 5 unlearning algorithms for comprehensive evaluation and comparative analysis, establishing a robust pipeline for federated LLM unlearning. Extensive experiments demonstrate that Oblivionis outperforms local training, achieving a robust balance between forgetting efficacy and model utility, with cross-algorithm comparisons providing clear directions for future LLM development.

In financial trading, factor models are widely used to price assets and capture excess returns from mispricing. Recently, we have witnessed the rise of variational autoencoder-based latent factor models, which learn latent factors self-adaptively. While these models focus on modeling overall market conditions, they often fail to effectively capture the temporal patterns of individual stocks. Additionally, representing multiple factors as single values simplifies the model but limits its ability to capture complex relationships and dependencies. As a result, the learned factors are of low quality and lack diversity, reducing their effectiveness and robustness across different trading periods. To address these issues, we propose a Spatio-Temporal factOR Model based on dual vector quantized variational autoencoders, named STORM, which extracts features of stocks from temporal and spatial perspectives, then fuses and aligns these features at the fine-grained and semantic level, and represents the factors as multi-dimensional embeddings. The discrete codebooks cluster similar factor embeddings, ensuring orthogonality and diversity, which helps distinguish between different factors and enables factor selection in financial trading. To show the performance of the proposed factor model, we apply it to two downstream experiments: portfolio management on two stock datasets and individual trading tasks on six specific stocks. The extensive experiments demonstrate STORM's flexibility in adapting to downstream tasks and superior performance over baseline models.

Federated recommender systems (FedRec) have emerged as a promising approach to provide personalized recommendations while protecting user privacy. However, recent studies have demonstrated their vulnerability to poisoning attacks, wherein malicious clients can inject carefully crafted gradients to prompt target items to benign users. Existing attacks typically target the full user group, which compromises stealth and increases the risk of detection. In contrast, real-world adversaries may prefer to target specific user subgroup, such as promoting health supplements to older individual, to maximize attack success while preserving stealth to evade detection. Motivated by this gap, we introduce Spattack, the first poisoning attack designed to manipulate recommendations for specific user subgroups in federated setting. Specifically, Spattack adopts an approximate-and-promote paradigm, which first approximate user embeddings of target/non-target subgroups and then prompts target items to the target subgroups. We further reveal a trade-off in achieving strong attack performance on the target group while keeping the non-target group largely unaffected. To achieve a better trade-off, we propose enhanced approximation and promotion strategies. For the approximation, we push the embeddings of different subgroup away based on contrastive learning and augment the target group's relevant item set via clustering. For the promotion, we align target and relevant item embeddings to strengthen their semantic connections. An adaptive weighting strategy is further proposed to balance promotion effects between target and non-target subgroups. Experiments on three real-world datasets demonstrate that Spattack consistently achieves strong attack performance on the target subgroup with minimal impact on non-target users, even when only 0.1% of users are malicious. Moreover, Spattack maintains competitive recommendation performance and exhibits strong resilience against mainstream defenses.

Federated Learning is a promising paradigm for privacy-preserving collaborative model training. In practice, it is essential not only to continuously train the model to acquire new knowledge but also to guarantee old knowledge the right to be forgotten (i.e., federated unlearning), especially for privacy-sensitive information or harmful knowledge. However, current federated unlearning methods face several challenges, including indiscriminate unlearning of cross-client knowledge, irreversibility of unlearning, and significant unlearning costs. To this end, we propose a method named FUSED, which first identifies critical layers by analyzing each layer’s sensitivity to knowledge and constructs sparse unlearning adapters for sensitive ones. Then, the adapters are trained without altering the original parameters, overwriting the unlearning knowledge with the remaining knowledge. This knowledge overwriting process enables FUSED to mitigate the effects of indiscriminate unlearning. Moreover, the introduction of independent adapters makes unlearning reversible and significantly reduces the unlearning costs. Finally, extensive experiments on three datasets across various unlearning scenarios demonstrate that FUSED’s effectiveness is comparable to Retraining, surpassing all other baselines while greatly reducing unlearning costs.

With the advent of sixth-generation (6G) technologies and growing communication demands, Low Earth Orbit (LEO) satellite networks have become essential in modern communications. However, due to the dynamic topology and complex network state of LEO environments, existing routing methods often fail to make effective decisions, limiting transmission performance. This paper proposes a LEO satellite routing method based on incremental evolutionary graph reinforcement learning (IEGRL). To address network state perception challenges, we introduce a topological learning model using deep graph attention (DGA), which captures complex inter-satellite connectivity and resource states. Additionally, by integrating incremental evolution strategies (IES) into deep reinforcement learning (DRL), we replace sequential interactive proximal policy optimization (PPO) with global parallel ES, achieving efficient routing convergence in the highly dynamic LEO environment. Experimental results demonstrate that our IEGRL approach enhances LEO network load balancing by reducing end-to-end (E2E) network latency, decreasing packet loss, and improving throughput compared with the benchmark approaches.

Federated Domain Adaptation (FDA) is a Federated Learning (FL) scenario where models are trained across multiple clients with unique data domains but a shared category space, without transmitting private data. The primary challenge in FDA is data heterogeneity, which causes significant divergences in gradient updates when using conventional averaging-based aggregation methods, reducing the efficacy of the global model. This further undermines both in-domain and out-of-domain performance (within the same federated system but outside the local client), which is critical in certain business applications. To address this, we propose a novel framework called \textbf{M}ulti-domain \textbf{P}rototype-based \textbf{F}ederated Fine-\textbf{T}uning (MPFT). MPFT fine-tunes a pre-trained model using multi-domain prototypes, i.e., several pretrained representations enriched with domain-specific information from category-specific local data. This enables supervised learning on the server to create a globally optimized adapter that is subsequently distributed to local clients, without the intrusion of data privacy. Empirical results show that MPFT significantly improves both in-domain and out-of-domain accuracy over conventional methods, enhancing knowledge preservation and adaptation in FDA. Notably, MPFT achieves convergence within a single communication round, greatly reducing computation and communication costs. To ensure privacy, MPFT applies differential privacy to protect the prototypes. Additionally, we develop a prototype-based feature space hijacking attack to evaluate robustness, confirming that raw data samples remain unrecoverable even after extensive training epochs. The complete implementation of MPFL is available at \url{https://anonymous.4open.science/r/DomainFL/}.

On-device large models (LMs) reduce cloud dependency but expose proprietary model weights to the end-user, making them vulnerable to white-box model stealing (MS) attacks. A common defense is TEE-Shielded DNN Partition (TSDP), which places all trainable LoRA adapters (fine tuned on private data) inside a trusted execution environment (TEE). However, this design suffers from excessive host-to-TEE communication latency. We propose AegisGuard, a fine tuning and deployment framework that selectively shields the MS sensitive adapters while offloading the rest to the GPU, balancing security and efficiency. AegisGuard integrates two key components: i) RL-based Sensitivity Measurement (RSM), which injects Gaussian noise during training and applies a lightweight reinforcement learning to rank adapters based on their impact on model stealing; and (ii) Shielded-Adapter Compression (SAC), which structurally prunes the selected adapters to reduce both parameter size and intermediate feature maps, further lowering TEE computation and data transfer costs. Extensive experiments demonstrate that AegisGuard achieves black-box level MS resilience (surrogate accuracy around 39%, matching fully shielded baselines), while reducing end-to-end inference latency by 2–3× and cutting TEE memory usage by 4× compared to state-of-the-art TSDP methods.

Federated Multi-Task Learning (FL-MTL) enables clients with heterogeneous data to collaboratively train models capable of handling multiple downstream tasks. However, FL-MTL faces key challenges, including statistical heterogeneity, task interference, and the need to balance local learning with global knowledge sharing. Traditional methods like FedAvg struggle in such settings due to the lack of explicit mechanisms to address these issues. In this paper, we propose FedRAM, a three-step framework that progressively updates two scalar hyperparameters: the task importance weight and the client aggregation coefficient. FedRAM introduces a reference-proxy-agent strategy, where the proxy model serves as an intermediate between the local reference model and the global agent model. This design reduces the need for repeated local training while preserving local performance. Extensive experiments on six real-world FL-MTL benchmarks show that FedRAM improves performance by at least 3$\%$ over the most baseline on both in-domain and out-of-domain tasks, while reducing computational cost by 15$\times$. These results make FedRAM a robust and practical solution for large-scale FL-MTL applications. The code is available at \url{https://github.com/wwffvv/FedRAM}.

As an important component of the space-air-ground integrated network, aerial base station (AeBS) systems have gained significant attention for their flexibility in mobility and cost-effective construction. Nevertheless, the scarce spectrum resources and difficulty in accessing global information bring necessity and challenges to the deployment and resource allocation of AeBSs. In this paper, we propose a practical two-timescale framework to solve the resource allocation and deployment optimization problem in multi-AeBS networks. Specifically, the subcarrier allocation problem is first transformed into a many-to-one matching game coupled with power allocation and solved in a small timescale. Then, in a large timescale, the AeBS deployment subproblem is transformed into a distributed partially observable Markov decision process (Dec-POMDP), and then a novel multi-agent hypergraph convolutional deep reinforcement learning (MAHGCDRL) is proposed to solve this problem. The proposed MAHGCDRL extracts features of neighboring AeBSs through hypergraph convolutional networks, enabling AeBS agents to achieve better coordination in a distributed manner. Simulation results show that our proposed approach can attain a higher sum rate, and the proposed MAHGCDRL algorithm achieves better learning performance compared to the existing benchmarks in the literature.

Federated Learning (FL) is a promising privacy-preserving machine learning paradigm that allows data owners to collaboratively train models while keeping their data localized. Despite its potential, FL faces challenges related to the trustworthiness of both clients and servers, particularly against curious or malicious adversaries. In this paper, we introduce a novel framework namedFederatedLearning with Low-DimensionalUpdateRepresentation andProximity-Based defense (FLURP), designed to address privacy preservation and resistance to Byzantine attacks in distributed learning environments. FLURP employs$\mathsf {LinfSample}$method, enabling clients to compute the$l_{\infty }$norm across sliding windows of updates, resulting in a Low-Dimensional Update Representation (LUR). Calculating the shared distance matrix among LURs, rather than updates, significantly reduces the overhead of Secure Multi-Party Computation (SMPC) by three orders of magnitude while effectively distinguishing between benign and poisoned updates. Additionally, FLURP integrates a privacy-preserving proximity-based defense mechanism utilizing optimized SMPC protocols to minimize communication rounds. Our experiments demonstrate FLURP's effectiveness in countering Byzantine adversaries with low communication and runtime overhead. FLURP offers a scalable framework for secure and reliable FL in distributed environments, facilitating its application in scenarios requiring robust data management and security.

The proliferation of end devices has led to a distributed computing paradigm, wherein on-device machine learning models continuously process diverse data generated by these devices. The dynamic nature of this data, characterized by continuous changes or data drift, poses significant challenges for on-device models. To address this issue, continual learning (CL) is proposed, enabling machine learning models to incrementally update their knowledge and mitigate catastrophic forgetting. However, the traditional centralized approach to CL is unsuitable for end devices due to privacy and data volume concerns. In this context, federated CL (FCL) emerges as a promising solution, preserving user data locally while enhancing models through collaborative updates. Aiming at the challenges of limited storage resources for CL, poor autonomy in task shift detection, and difficulty in coping with new adversarial tasks in the FCL scenario, we propose a novel FCL framework named self-adaptive federated CL (SacFL). $\rm {SacFL}$ employs an encoder-decoder architecture to separate task-robust and task-sensitive components, significantly reducing storage demands by retaining lightweight task-sensitive components for resource-constrained end devices. Moreover, $\rm {SacFL}$ leverages contrastive learning to introduce an autonomous data shift detection mechanism, enabling it to discern whether a new task has emerged and whether it is a benign task. This capability ultimately allows the device to autonomously trigger CL or attack defense strategy without additional information, which is more practical for end devices. Comprehensive experiments conducted on multiple text and image datasets, such as Cifar100 and THUCNews, have validated the effectiveness of $\rm {SacFL}$ in both class-incremental and domain-incremental scenarios. Furthermore, a demo system has been developed to verify its practicality.

The physical-virtual world synchronization to develop the Metaverse will require a massive transmission and exchange of data. In this paper, we introduce semantic communication for the development of virtual transportation networks in the Metaverse. Leveraging the perception capabilities of edge devices, virtual service providers (VSPs) can subscribe to their preferred edge devices to receive the semantic data of interest. However, the demands of the VSPs are highly dependent on the users that they are serving. To address the resource allocation problem amid stochastic user demand, we propose a stochastic semantic transmission scheme (SSTS) based on two-stage stochastic integer programming. Using real data captured by edge devices we deploy in Singapore, the simulation results show that SSTS can minimize the transmission cost of the VSPs while accounting for the users' demand uncertainties.

The utilization of emergent Generative Artificial Intelligence (GAl) within the realm of Internet of Vehicles (loV) can augment edge intelligence, thereby catering to the diverse content-generation needs of novel in-vehicle services. Nonethe-less, existing cloud-centric GAl paradigms are not inherently suitable for wireless vehicular networks, primarily due to their extensive computing requirements, lack of specificity, and spatial detachment from end users. To cope with these challenges, we introduce an innovative Generative 10 V (g 10 V)architecture that employs a collaborative fine-tuning mechanism for pre-trained GAl models. The mechanism is mainly orchestrated collaboratively by Road-Side Units (RSUs) and vehicles within a Federated Learning (FL) paradigm. Here, we take text-to-image diffusion models as typical examples to show the co-fine-tuning workflow in detail, aiming to utilize edge traffic data to realize rapid, customized, and lightweight GAl in the resource-limited 10 V scenario. Thereafter, we formulate the problem of edge communication and computation resource allocation during RSU-vehicle co-fine-tuning, which is pivotal for optimizing time and energy consumption within this process. To address the challenge, we deploy a Self-adaptive Harmony Search (SHS)-based resource allocation strategy. Experiments based on Stable Diffusion vl-4 model validate the excellent performance in image generating and the time and energy consumption during co-fine-tuning in resource-limited and fast-changing 10 V scenarios.

The increasing focus on privacy and security in 6G networks, which are intelligence-native, necessitates the use of quantum key distribution-secured semantic information communication (QKD-SIC) to protect confidential data. In QKD-SIC systems, edge devices connected via quantum channels can efficiently encrypt semantic information from the semantic source, and securely transmit the encrypted semantic information to the semantic destination. In this article, we consider an efficient resource (i.e., quantum key distribution (QKD) and KM wavelengths) sharing problem to support QKD-SIC systems under the uncertainty of semantic information generated by edge devices. In such a system, QKD service providers offer QKD services with different subscription options to the edge devices. The QKD services are envisioned to follow cloud computing that has the subscription in the reservation and on-demand options, i.e., for long and short (immediate) terms, respectively. As such, to reduce the cost for the edge device users, we propose a QKD resource management framework for the edge devices communicating semantic information. The framework is based on a two-stage stochastic optimization model to achieve optimal QKD deployment. Moreover, to reduce the deployment cost of QKD service providers, QKD resources in the proposed framework can be utilized based on efficient QKD-SIC resource management, including semantic information transmission among edge devices, secret-key provisioning, and cooperation formation among QKD service providers. In detail, the formulated two-stage stochastic optimization model can achieve the optimal QKD-SIC resource deployment while meeting the secret-key requirements for semantic information transmission of edge devices. Moreover, to share the cost of the QKD resource pool among cooperative QKD service providers forming a coalition in a fair and interpretable manner, the proposed framework leverages the concept of Shapley value from cooperative game theory as a solution. Experimental results demonstrate that the proposed framework can reduce the deployment cost by about 40% compared with existing noncooperative baselines.

Federated Learning(FL) has attracted wide research interest due to its potential in building machine learning models while preserving users' data privacy. However, due to the distributive nature of FL, it is vulnerable to misbehavior from participating worker nodes. Thus, it is important to select clients to participate in FL. Recent studies on FL client selection focus on the perspective of improving model training efficiency and performance, without holistically considering potential misbehavior and the cost of hiring. To bridge this gap, we propose a first-of-its-kind reputation-awareStochastic integer programming-based FLClientSelection method (SCS). It can optimally select and compensate clients with different reputation profiles. Extensive experiments show that SCS achieves the most advantageous performance-cost trade-off compared to other existing state-of-the-art approaches.

To enable ubiquitous Artificial Intelligence (AI) in the next-generation wireless communications networks, computation-intensive tasks such as data processing and model training have to be performed by energy-constrained end users. In this paper, we present a hybrid coded edge computing network whereby users can choose to complete their computation task through: i) local computation with the wireless power transfer derived from base stations, ii) coded edge offloading, or iii) hybrid computation involving edge offloading and local computation. To minimize the overall network cost, we propose a stochastic resource optimization approach. Given the stochastic nature of wireless charging efficiency and edge servers computation capacities, which can only be observedex-post, a computation strategy for each user is determined using the two-stage stochastic integer programming (SIP). To address the complexity of the SIP problem which scales with the size of the network, we introduce the efficient computation methods of Benders’ decomposition and sample average approximation. Besides, we present a special case of$z$-stage stochastic offloading optimization that is applicable when the corrective edge offloading action can be executed in multiple stages, e.g., for non-time-sensitive tasks that do not need to be completed by stage two. Finally, we provide extensive sensitivity analyses to evaluate the performance of the proposed cost minimization approach amid varying network parameters. We demonstrate that our approach outperforms deterministic optimization approaches for in-network cost minimization.

With the recent development of the Metaverse, people are more connected with each other. Avatars are used to represent the people, to communicate with one another, and they can build the community virtually. In these processes, a massive amount of data is exchanged between the physical and the virtual world. However, the existing communication technologies are insufficient to support the Metaverse, and the energy consumption of the Metaverse is huge. Therefore, semantic communication is one of the emerging communication paradigms to reduce the size of the data transmitted and reduce energy consumption while maintaining its meaning. Virtual service providers (VSPs) who provide services in the Metaverse can purchase semantic data from the nearby edge sensing units by using two subscription plans: reservation and on-demand. However, in practice, the demand of the VSPs is uncertain due to the variability of the Metaverse. To minimize the cost of the network and prevent over- and under-subscription of the resources, we propose a two-phase stochastic semantic resource allocation (SSRA) scheme. In phase one, a double dutch auction performs a one-to-one matching between VSPs and edge sensing units. The matching is dynamic and depends on the quality of experience (QoE) from the Metaverse users and the semantic data transmission cost from the edge sensing units. The matching changes whenever QoE and the semantic data transmission cost vary. In phase two, we consider the demand uncertainty and matching result from the phase one to formulate a distributed robust optimization (DRO) problem to minimize the operation cost of the VSPs. Using a real-world dataset, simulation results demonstrate that our proposed scheme is fully dynamic and minimizes the operation cost/energy consumption of VSPs in the presence of stochastic uncertainties.

Metaverse provides embodied artificial-reality experience to the users in the virtual spaces. Many innovative and creative services such as virtual conference and tourism have been realized in the digital twins maintained by the virtual service providers (VSP) in Metaverse. Digital twins are digital copies of the physical world constructed virtually by the VSPs using real-world data. For a realistic experience, VSPs need to collect data that is up-to-date and relevant to their services. In this paper, we propose an incentive design framework to support the data trading between VSPs and edge devices. In the auction model, we model the valuation of data by considering data relatedness and data freshness. In our model, the semantic communication model is used to filter the relevant data, and the age of information (AoI) metric is used to assess the data freshness. Results show that by considering the data freshness, our mechanism helps to increase the average update frequency so that the VSPs obtain fresh data for construction of digital twins. Our model ensures the desired properties of individual rationality, incentive compatibility, and budget balance.

Recent breakthroughs in generative artificial intelligence have triggered a surge in demand for machine learning training, which poses significant cost burdens and environmental challenges due to its substantial energy consumption. Scheduling training jobs among geographically distributed cloud data centers unveils the opportunity to optimize the usage of computing capacity powered by inexpensive and low-carbon energy and address the issue of workload imbalance. To tackle the challenge of multi-objective scheduling, i.e., maximizing GPU utilization while reducing operational costs, we propose an algorithm based on multi-agent reinforcement learning and actor-critic methods to learn the optimal collaborative scheduling strategy through interacting with a cloud system built with real-life workload patterns, energy prices, and carbon intensities. Compared with other algorithms, our proposed method improves the system utility by up to 28.6% attributable to higher GPU utilization, lower energy cost, and less carbon emission.

Vehicles on the road generate a large amount of data, which often can be used to train models for destination prediction and traffic flow prediction in intelligent transportation systems (ITS). To break down the information silos and further strengthen privacy protection, we leverage federated learning and differential privacy in this paper. In order to motivate the participation of data owners, we further devise a single-leader multi-follower Stackelberg game incentive mechanism which accounts for the heterogeneous privacy budgets and participation costs of vehicle owners. Due to the lack of prior knowledge, deep reinforcement learning is used to obtain the approximate solution for each player to achieve the Stackelberg equilibrium. Our proposed framework is capable of achieving a solution close to the Nash Equilibrium.

As an emerging privacy-preserving collaborative machine learning paradigm, the success of federated learning (FL) relies heavily on effectively motivating data owners (a.k.a. FL clients) to contribute high-quality local data and computational resources towards FL model training. Rewarding clients with incentives has been identified as a useful approach towards this goal. It is often implemented in conjunction with auction-based federated learning (AFL). Nevertheless, this approach introduces new challenges for FL servers (a.k.a. federations) as they must work within a limited budget and make trade-off decisions between hiring FL clients, saving costs and achieving target model performance. The dynamic nature of AFL further complicates this problem as federations need to consider potential competition from other federations. To address this challenge, we propose the Reputation-aware Opportunistic Budget Optimization approach for Auction-based Federated Learning (ROBO-AFL). Based on Lyapunov optimization, it helps federations maximize their utility by determining the time-averaged optimal allocation of budget for the hiring FL clients. Extensive experimental evaluation based on real-world data demonstrates that compared to four state-of-the-art approaches, ROBO-AFL achieves the most advantageous trade-off between fairness, cost-effectiveness and utility with 1.80% higher utility with 62.85% lower cost than the best-performing baseline, while maintaining a comparably high level of fairness. To the best of our knowledge, ROBO-AFL is the first decision support approach designed to help federations optimize their budget usage in competitive and open AFL markets.

Unmanned aerial vehicles (UAVs) have gained wide research interests due to their technological advancement and high mobility. The UAVs are equipped with increasingly advanced capabilities to run computationally intensive applications enabled by machine learning techniques. However, because of both energy and computation constraints, the UAVs face issues hovering in the sky while performing computation due to weather uncertainty. To overcome the computation constraints, the UAVs can partially or fully offload their computation tasks to the edge servers. In ordinary computation offloading operations, the UAVs can retrieve the result from the returned output. Nevertheless, if the UAVs are unable to retrieve the entire result from the edge servers, i.e., straggling edge servers, this operation will fail. In this article, we propose a coded distributed computing (CDC) approach for computation offloading to mitigate straggling edge servers. The UAVs can retrieve the returned result when the number of returned copies is greater than or equal to the recovery threshold. There is a shortfall if the returned copies are less than the recovery threshold. To minimize the cost of the network, energy consumption by the UAVs, and prevent over and under subscription of the resources, we devise a two-phase stochastic coded offloading scheme (SCOS). In the first phase, the appropriate UAVs are allocated to the charging stations amid weather uncertainty. In the second phase, we use the$z$-stage stochastic integer programming (SIP) to optimize the number of computation subtasks offloaded and computed locally, while taking into account the computation shortfall and demand uncertainty. By using a real data set, the simulation results show that our proposed scheme is fully dynamic and minimizes the cost of the network and UAV energy consumption amid stochastic uncertainties.

Amid data privacy concerns, Federated Learning (FL) has emerged as a promising machine learning paradigm that enables privacy-preserving collaborative model training. However, there exists a need for a platform that matches data owners (supply) with model requesters (demand). In this paper, we present CrowdFL, a platform to facilitate the crowdsourcing of FL model training. It coordinates client selection, model training, and reputation management, which are essential steps for the FL crowdsourcing operations. By implementing model training on actual mobile devices, we demonstrate that the platform improves model performance and training efficiency. To the best of our knowledge, it is the first platform to support crowdsourcing-based FL on edge devices.

As countries enter the endemic phase of COVID-19, people's risk of exposure to the virus is greater than ever. There is a need to make more informed decisions in our daily lives on avoiding crowded places. Crowd monitoring systems typically require costly infrastructure. We propose a crowd-sourced crowd monitoring platform which leverages user inputs to generate crowd counts and forecast location crowdedness. A key challenge for crowd-sourcing is a lack of incentive for users to contribute. We propose a Reinforcement Learning based dynamic incentive mechanism to optimally allocate rewards to encourage user participation.

On behalf of the Program Committee of the 20th IEEE international conference on embedded and ubiquitous computing (EUC 2022), we would like to offer our great welcome to you to attend the conference in person in Wuhan, China, 28-30 October 2022, or virtually online.

The semantic communication system enables wireless devices to communicate effectively with the semantic meaning of the data. Wireless powered Internet of Things (IoT) that adopts the semantic communication system relies on harvested energy to transmit semantic information. However, the issue of energy constraint in the semantic communication system is not well studied. In this paper, we propose a semantic-based energy valuation and take an economic approach to solve the energy allocation problem as an incentive mechanism design. In our model, IoT devices (bidders) place their bids for the energy and power transmitter (auctioneer) decides the winner and payment by using deep learning based optimal auction. Results show that the revenue of wireless power transmitter is maximized while satisfying Individual Rationality (IR) and Incentive Compatibility (IC).

Leveraging on the wealth of data and advancements in Artificial Intelligence, smart cities have demonstrated their great potential in providing solutions to challenges that the urban population faces today. However, as the urban population becomes more privacy sensitive and with the introduction of stringent privacy regulations, the differential-private FL (DPFL) is a promising technology that can enable privacy-preserving collaborative model training. In this paper, we consider an FL network of model owners and data owners with heterogeneous privacy budgets and preferences respectively. In exchange for their participation in the training, the model owner offers a reward pool that is shared among the data owners that take part in the FL training. In turn, the FL worker with heterogeneous privacy preferences may select the model owner to contribute its parameters to. To model the dynamic and strategic behaviour of the workers in the process of model owner selection, we propose an evolutionary game approach. Then, we conduct simulations to validate the evolutionary equilibrium, as well as provide the sensitivity analyses of the model.

Dubbed as the next-generation Internet, the meta-verse is a virtual world that allows users to interact with each other or objects in real-time using their avatars. The metaverse is envisioned to support novel ecosystems of service provision in an immersive environment brought about by an intersection of the virtual and physical worlds. The native AI systems in metaverse will personalized user experience over time and shape the experience in a scalable, seamless, and synchronous way. However, the metaverse is characterized by diverse resource types amid a highly dynamic demand environment. In this paper, we propose the case study of virtual education in the metaverse and address the unified resource allocation problem amid stochastic user demand. We propose a stochastic optimal resource allocation scheme (SORAS) based on stochastic integer programming with the objective of minimizing the cost of the virtual service provider. The simulation results show that SORAS can minimize the cost of the virtual service provider while accounting for the users’ demands uncertainty.

With the ubiquitous sensing enabled by the Internet-of-Things (IoT), massive amount of data is generated every second, transforming the way we interact with the world. To manage big data and enable analytics at the edge of the network, large amount of computation power is required to perform the computation intensive tasks. However, the energy-constrained IoT devices are not able to perform the computation tasks without compromising the quality-of-service of the applications. In this paper, we propose a hybrid network in which users can offload their computation tasks to edge servers through coded edge offloading or perform local computation with the wireless power transfer derived from coalitions of unmanned aerial vehicles (UAVs) serving as mobile charging stations. We consider a two-level optimization approach where an optimal UAV coalitional structure that minimizes the network cost is formed. In the performance evaluation, we provide extensive sensitivity analyses to study the performance of the cost minimization approach amid varying network parameters.

Federated Learning (FL) is a privacy-preserving collaborative learning approach that trains artificial intelligence (AI) models without revealing local datasets of the FL workers. While FL ensures the privacy of the FL workers, its performance is limited by several bottlenecks, which become significant given the increasing amounts of data generated and the size of the FL network. One of the main challenges is the straggler effects where the significant computation delays are caused by the slow FL workers. As such, Coded Federated Learning (CFL), which leverages coding techniques to introduce redundant computations to the FL server, has been proposed to reduce the computation latency. In CFL, the FL server helps to compute a subset of the partial gradients based on the composite parity data and aggregates the computed partial gradients with those received from the FL workers. In order to implement the coding schemes over the FL network, incentive mechanisms are important to allocate the resources of the FL workers and data owners efficiently in order to complete the CFL training tasks. In this paper, we consider a two-level incentive mechanism design problem. In the lower level, the data owners are allowed to support the FL training tasks of the FL workers by contributing their data. To model the dynamics of the selection of FL workers by the data owners, an evolutionary game is adopted to achieve an equilibrium solution. In the upper level, a deep learning based auction is proposed to model the competition among the model owners.

For several industrial applications, a sole data owner may lack sufficient training samples to train effective machine learning based models. As such, we propose a federated learning (FL) based approach to promote privacy-preserving collaborative machine learning for applications in smart industries. In our system model, a model owner initiates an FL task involving a group of workers, i.e., data owners, to perform model training on their locally stored data before transmitting the model updates for aggregation. There exists a tradeoff between service latency, i.e., the time taken for the training request to be completed, and age of information (AoI), i.e., the time elapsed between data aggregation from the deployed industrial Internet of Things devices to completion of the FL-based training. On one hand, if the data are collected only upon the model owner's request, the AoI is low. On the other hand, the service latency incurred is more significant. Furthermore, given that different training tasks may have varying AoI requirements, we propose a contract-theoretic task-aware incentive scheme that can be calibrated based on the weighted preferences of the model owner toward AoI and service latency. The performance evaluation validates the incentive compatibility of our contract amid information asymmetry, and shows the flexibility of our proposed scheme toward satisfying varying preferences of AoI and service latency.

To enable the large scale and efficient deployment of Artificial Intelligence (AI), the confluence of AI and Edge Computing has given rise to Edge Intelligence, which leverages on the computation and communication capabilities of end devices and edge servers to process data closer to where it is produced. One of the enabling technologies of Edge Intelligence is the privacy preserving machine learning paradigm known as Federated Learning (FL), which enables data owners to conduct model training without having to transmit their raw data to third-party servers. However, the FL network is envisioned to involve thousands of heterogeneous distributed devices. As a result, communication inefficiency remains a key bottleneck. To reduce node failures and device dropouts, the Hierarchical Federated Learning (HFL) framework has been proposed whereby cluster heads are designated to support the data owners through intermediate model aggregation. This decentralized learning approach reduces the reliance on a central controller, e.g., the model owner. However, the issues of resource allocation and incentive design are not well-studied in the HFL framework. In this article, we consider a two-level resource allocation and incentive mechanism design problem. In the lower level, the cluster heads offer rewards in exchange for the data owners' participation, and the data owners are free to choose which cluster to join. Specifically, we apply the evolutionary game theory to model the dynamics of the cluster selection process. In the upper level, each cluster head can choose to serve a model owner, whereas the model owners have to compete amongst each other for the services of the cluster heads. As such, we propose a deep learning based auction mechanism to derive the valuation of each cluster head's services. The performance evaluation shows the uniqueness and stability of our proposed evolutionary game, as well as the revenue maximizing properties of the deep learning based auction.

Amid growing concerns on data privacy, Federated Learning (FL) has emerged as a promising privacy preserving distributed machine learning paradigm. Given that the FL network is expected to be implemented at scale, several studies have proposed system architectures towards improving the network scalability and efficiency. Specifically, the Hierarchical FL (HFL) network utilizes cluster heads, e.g., base stations, for the intermediate aggregation and relay of model parameters. Serverless FL is also proposed recently, in which the data owners, i.e., workers, exchange the local model parameters among a neighborhood of workers. This decentralized approach reduces the risk of a single point of failure but inevitably incurs significant communication overheads. To achieve the best of both worlds, we propose the Serverless Hierarchical Federated Learning (SHFL) framework in this paper. The SHFL framework adopts a two-layer system architecture. In the lower layer, the FL workers are grouped into clusters under cluster heads. In the upper layer, the cluster heads exchange the intermediate parameters with their one-hop neighbors without the aid of a central server. To improve the sustainable efficiency of the FL system while taking into account the incentive design for workers marginal contributions in the system, we propose the reputation-aware hedonic coalition formation game in this paper. Specifically, the workers are rewarded for their marginal contribution to the cluster, whereas the reputation opinions of each cluster head is updated in a decentralized manner, thereby deterring malicious behaviors by the cluster head. This improves the performance of the network since cluster heads with higher reputation scores are more reliable in relaying the intermediate model parameters. The simulation results show that our proposed hedonic coalition formation algorithm converges to a Nash-stable partition and improves the network efficiency.

The COVID-19 pandemic is one of the most severe challenges the world faces today. In order to contain the transmission of COVID-19, people around the world have been advised to practise social distancing. However, maintaining social distance is a challenging problem, as we often do not know beforehand how crowded the places we intend to visit are. In this paper, we demonstrate crowded.sg, an AI-empowered platform that leverages on Unmanned Aerial Vehicles (UAVs), crowdsourced images, and computer vision techniques to provide social distancing decision support.

Today, modern unmanned aerial vehicles (UAVs) are equipped with increasingly advanced capabilities that can run applications enabled by machine learning techniques, which require computationally intensive operations such as matrix multiplications. Due to computation constraints, the UAVscan offload their computation tasks to edge servers. To mitigate stragglers, coded distributed computing (CDC) based offloading can be adopted. In this paper, we propose an Optimal Task Allocation Scheme (OTAS) based on Stochastic Integer Programming with the objective to minimize energy consumption during computation offloading. The simulation results show that amid uncertainty of task completion, the energy consumption in the UAV network is minimized.

Parkinson’s disease (PD) is a chronic disease with a high risk of incidence after the age of 60 and is a problem for many countries facing an aging population. Current works have mainly focused on supervised learning using data collected from various sensors to differentiate between PD and healthy subjects. However, such supervised methods are not ideal for prognosis where there are no labels (i.e., we do not know in advance which subjects will develop PD in the future). We propose to tackle the problem as a semi-supervised anomaly detection task, where we model the physiological patterns of healthy subjects instead. A self-supervised learning technique first learns a good representation of the sensor signals. The representations are then adapted to capture inter-class patterns for anomaly detection. Evaluation on a large-scale PD dataset shows that our approach can learn discriminative features.

As the amount of data collected for crowdsensing applications increases rapidly due to improved sensing capabilities and the increasing number of Internet of Things (IoT) devices, the cloud server is no longer able to handle the large-scale datasets individually. Given the improved computational capabilities of the edge devices, coded distributed computing has become a promising approach given that it allows computation tasks to be carried out in a distributed manner while mitigating straggler effects, which often account for the long overall completion times. Specifically, by using polynomial codes, computed results from only a subset of devices are needed to reconstruct the final result. However, there is no incentive for the edge devices to complete the computation tasks. In this paper, we present an all-pay auction to incentivize the edge devices to participate in the coded computation tasks. In this auction, the bids of the edge devices are represented by the allocation of their Central Processing Unit (CPU) power to the computation tasks. All edge devices submit their bids regardless of whether they win or lose in the auction. The all-pay auction is designed to maximize the utility of the cloud server by determining the reward allocation to the winners. Simulation results show that the edge devices are incentivized to allocate more CPU power when multiple rewards are offered instead of a single reward.

The COVID-19 pandemic has disrupted the lives of millions across the globe. In Singapore, promoting safe distancing by managing crowds in public areas have been the cornerstone of containing the community spread of the virus. One of the most important solutions to maintain social distancing is to monitor the crowdedness of indoor and outdoor points of interest. Using Nanyang Technological University (NTU) as a testbed, we develop and deploy a platform that provides live and predicted crowd counts for key locations on campus to help users plan their trips in an informed manner, so as to mitigate the risk of community transmission.

Federated Edge Learning (FEL) is a distributed Machine Learning (ML) framework for collaborative training on edge devices. FEL improves data privacy over traditional centralized ML model training by keeping data on the devices and only sending local model updates to a central coordinator for aggregation. However, challenges still remain in existing FEL architectures where there is high communication overhead between edge devices and the coordinator. In this paper, we present a working prototype of blockchain-empowered and communication-efficient FEL framework, which enhances the security and scalability towards large-scale implementation of FEL.

Federated Learning (FL) is a privacy-preserving collaborative learning approach that trains artificial intelligence (AI) models without revealing local datasets of the FL workers. One of the main challenges is the straggler effects where the significant computation delays are caused by the slow FL workers. As such, Coded Federated Learning (CFL), which leverages coding techniques to introduce redundant computations to the FL server, has been proposed to reduce the computation latency. In order to implement the coding schemes over the FL network, incentive mechanisms are important to allocate the resources of the FL workers and data owners efficiently in order to complete the CFL training tasks. In this paper, we consider a two-level incentive mechanism design problem. In the lower level, the data owners are allowed to support the FL training tasks of the FL workers by contributing their data. To model the dynamics of the selection of FL workers by the data owners, an evolutionary game is adopted to achieve an equilibrium solution. In the upper level, a deep learning based auction is proposed to model the competition among the model owners.

Federated Learning (FL) is a promising privacy-preserving distributed machine learning paradigm. However, communication inefficiency remains the key bottleneck that impedes its large-scale implementation. Recently, hierarchical FL (HFL) has been proposed in which data owners, i.e., workers, can first transmit their updated model parameters to edge servers for intermediate aggregation. This reduces the instances of global communication and straggling workers. To enable efficient HFL, it is important to address the issues of edge association in the context of non-cooperative players, i.e., workers, edge servers, and model owner. However, the existing studies merely focus on static approaches and do not consider the dynamic interactions and bounded rationalities of the players. In this paper, we propose the edge association strategies of the workers to be modelled using an evolutionary game. Then, we provide numerical results to validate that our proposed framework captures the HFL system dynamics under varying sources of network heterogeneity.

Currently, the data collected by the Internet of Healthcare Things, i.e., healthcare oriented Internet of Things (IoT), still rely on cloud-based centralized data aggregation and processing. To reduce the need for transmission of data to the cloud, the edge computing architecture may be adopted to facilitate machine learning at the edge of the network through leveraging on the amassed computation resources of pervasive IoT devices. In this article, federated learning (FL) is proposed to enable privacy-preserving collaborative model training at the edge of the network across distributed IoT users. However, the users in the FL network may have different willingness to participate (WTP), a hidden information unknown to the model owner. Furthermore, the development of healthcare applications typically requires sustainable user participation, e.g., for the continuous collection of data during which a user’s WTP may change over time. As such, we leverage on the dynamic contract design to consider a two-period incentive mechanism that satisfies the intertemporal incentive compatibility (IIC), such that the self-revealing mechanism of the contract holds across both periods. The performance evaluation shows that our contract design satisfies the IIC constraints and derives greater profits than that of the uniform pricing scheme, thus validating its effectiveness in mitigating the adverse impacts of the information asymmetry.

Due to air quality significantly affects human health, it is becoming increasingly important to accurately and timely predict the air quality index (AQI). To this end, this article proposes a new federated learning (FL)-based aerial-ground air quality sensing framework for fine-grained 3-D air quality monitoring and forecasting. Specifically, in the air, this framework leverages a lightweight Dense-MobileNet model to achieve energy-efficient end-to-end learning from haze features of haze images taken by unmanned aerial vehicles (UAVs) for predicting AQI scale distribution. Furthermore, the FL framework not only allows various organizations or institutions to collaboratively learn a well-trained global model to monitor AQI without compromising privacy but also expands the scope of UAV swarms monitoring. For ground sensing systems, we propose a graph convolutional neural network-based long short-term memory (GC-LSTM) model to achieve accurate, real time, and future AQI inference. The GC-LSTM model utilizes the topological structure of the ground monitoring station to capture the spatiotemporal correlation of historical observation data, which helps the aerial-ground sensing system to achieve accurate AQI inference. Through extensive case studies on a real-world data set, numerical results show that the proposed framework can achieve accurate and energy-efficient AQI sensing without compromising the privacy of raw data.

Federated Learning (FL) is a promising privacy-preserving distributed machine learning paradigm. However, communication inefficiency remains the key bottleneck that impedes its large-scale implementation. Recently, hierarchical FL (HFL) has been proposed in which data owners, i.e., workers, can first transmit their updated model parameters to edge servers for intermediate aggregation. This reduces the instances of global communication and straggling workers. To enable efficient HFL, it is important to address the issues of edge association and resource allocation in the context of non-cooperative players, i.e., workers, edge servers, and model owner. However, the existing studies merely focus on static approaches and do not consider the dynamic interactions and bounded rationalities of the players. In this paper, we propose a hierarchical game framework to study the dynamics of edge association and resource allocation in self-organizing HFL networks. In the lower-level game, the edge association strategies of the workers are modelled using an evolutionary game. In the upper-level game, a Stackelberg differential game is adopted in which the model owner decides an optimal reward scheme given the expected bandwidth allocation control strategy of the edge server. Finally, we provide numerical results to validate that our proposed framework captures the HFL system dynamics under varying sources of network heterogeneity.

Coupled with the rise of Deep Learning, the wealth of data and enhanced computation capabilities of Internet of Vehicles (IoV) components enable effective Artificial Intelligence (AI) based models to be built. Beyond ground data sources, Unmanned Aerial Vehicles (UAVs) based service providers for data collection and AI model training, i.e., Drones-as-a-Service (DaaS), is becoming increasingly popular in recent years. However, the stringent regulations governing data privacy potentially impedes data sharing across independently owned UAVs. To this end, we propose the adoption of a Federated Learning (FL) based approach to enable privacy-preserving collaborative Machine Learning across a federation of independent DaaS providers for the development of IoV applications, e.g., for traffic prediction and car park occupancy management. Given the information asymmetry and incentive mismatches between the UAVs and model owners, we leverage on the self-revealing properties of a multi-dimensional contract to ensure truthful reporting of the UAV types, while accounting for the multiple sources of heterogeneity, e.g., in sensing, computation, and transmission costs. Then, we adopt the Gale-Shapley algorithm to match the lowest cost UAV to each subregion. The simulation results validate the incentive compatibility of our contract design, and shows the efficiency of our matching, thus guaranteeing profit maximization for the model owner amid information asymmetry.

Due to the advanced capabilities of the Internet of Vehicles (IoV) components such as vehicles, Roadside Units (RSUs) and smart devices as well as the increasing amount of data generated, Federated Learning (FL) becomes a promising tool given that it enables privacy-preserving machine learning that can be implemented in the IoV. However, the performance of the FL suffers from the failure of communication links and missing nodes, especially when continuous exchanges of model parameters are required. Therefore, we propose the use of Unmanned Aerial Vehicles (UAVs) as wireless relays to facilitate the communications between the IoV components and the FL server and thus improving the accuracy of the FL. However, a single UAV may not have sufficient resources to provide services for all iterations of the FL process. In this paper, we present a joint auction-coalition formation framework to solve the allocation of UAV coalitions to groups of IoV components. Specifically, the coalition formation game is formulated to maximize the sum of individual profits of the UAVs. The joint auction-coalition formation algorithm is proposed to achieve a stable partition of UAV coalitions in which an auction scheme is applied to solve the allocation of UAV coalitions. The auction scheme is designed to take into account the preferences of IoV components over heterogeneous UAVs. The simulation results show that the grand coalition, where all UAVs join a single coalition, is not always stable due to the profit-maximizing behavior of the UAVs. In addition, we show that as the cooperation cost of the UAVs increases, the UAVs prefer to support the IoV components independently and not to form any coalition.

Beyond ground data sources, Unmanned Aerial Vehicles (UAVs) based service providers for data collection and AI model training, i.e., Drones-as-a-Service (DaaS), is increasingly popular in the Internet of Vehicles (IoV) applications in recent years. However, the stringent regulations governing data privacy potentially impedes data sharing across independently owned UAVs. To this end, we propose the adoption of a Federated Learning (FL) based approach to enable privacy-preserving collaborative Machine Learning for the development of IoV applications, e.g., for traffic prediction and car park occupancy management. Given the information asymmetry and incentive mismatches between the UAVs and model owner, we leverage on the self-revealing properties of a multi-dimensional contract to ensure truthful reporting of the UAV types, while accounting for the multiple sources of heterogeneity, e.g., in sensing and transmission costs. Then, we adopt the Gale-Shapley algorithm to match the lowest cost UAV to each subregion. The simulation results validate the incentive compatibility of our contract design and shows the efficiency of our matching.

With the rapid development of the Industrial Internet of Things (IIoT), various IoT devices and sensors generate massive industrial sensing data. Sensing big data can be analyzed for insights that lead to better decisions and strategic industrial production by using advanced machine learning technologies. However, vulnerable IoT devices are easy to be compromised thus causing IoT devices failures (i.e., anomalies). The anomalies seriously affect the production of industrial products, thereby, it is increasingly important to accurately and timely detect anomalies. To this end, we first introduce a Federated Learning (FL) framework to enable decentralized edge devices to collaboratively train a Deep Anomaly Detection (DAD) model, which can improve its generalization ability. Second, we propose a Convolutional Neural Network-Long Short Term Memory (CNN-LSTM) model to accurately detect anomalies. The CNN-LSTM model uses CNN units to capture fine-grained features and retains the advantages of LSTM unit in predicting time series data. Third, to achieve real-time and lightweight anomaly detection in the proposed framework, a gradient compression mechanism is applied to reduce communication costs and improve communication efficiency. Extensive experiment results based on realworld datasets demonstrate that the proposed framework and mechanism can accurately and timely detect anomalies, and also reduce about 50% communication overhead when compared with traditional schemes.

Due to the advanced capabilities of the Internet of Vehicles (IoV) components such as vehicles, Roadside Units (RSUs) and smart devices as well as the increasing amount of data generated, Federated Learning (FL) becomes a promising tool given that it enables privacy-preserving machine learning. However, the performance of the FL suffers from the failure of communication links and missing nodes. Therefore, we propose the use of Unmanned Aerial Vehicles (UAVs) as wireless relays to facilitate the communications between the IoV components and the FL server and thus improving the accuracy of the FL. However, a single UAV may not have sufficient resources for all iterations of the FL process. In this paper, we present a joint auction-coalition formation framework. The joint auctioncoalition formation algorithm is proposed to achieve a stable partition of UAV coalitions in which an auction scheme is applied. The auction scheme is designed to take into account the preferences of IoV components over heterogeneous UAVs. The simulation results show that the grand coalition, where all UAVs join a single coalition, is not always stable due to the profitmaximizing behavior of the UAVs. In addition, we show that as the cooperation cost of the UAVs increases, the UAVs prefer not to form any coalition.

One of the enabling technologies of Edge Intelligence is the privacy preserving machine learning paradigm called Federated Learning (FL). However, communication inefficiency remains a key bottleneck in FL. To reduce node failures and device dropouts, the Hierarchical Federated Learning (HFL) framework has been proposed whereby cluster heads are designated to support the data owners through intermediate model aggregation. This decentralized learning approach reduces the reliance on a central controller, e.g., the model owner. However, the issues of resource allocation and incentive design are not well-studied in the HFL framework. In this paper, we consider a two-level resource allocation and incentive mechanism design problem. In the lower level, the cluster heads offer rewards in exchange of the data owners' participation, and the data owners are free to choose among any clusters to join. Specifically, we apply the evolutionary game theory to model the dynamics of the cluster selection process. In the upper level, given that each cluster head can choose to serve a model owner, the model owners have to compete for the services of the cluster head. As such, we propose a deep learning based auction mechanism to derive the valuation of each cluster head's services. The performance evaluation shows the uniqueness and stability of our proposed evolutionary game, as well as the revenue maximizing property of the deep learning based auction.

In the Internet of Vehicles (IoV) paradigm, a model owner is able to leverage on the enhanced capabilities of Intelligent Connected Vehicles (ICV) to develop promising Artificial Intelligence (AI) based applications, e.g., for traffic efficiency. However, in some cases, a model owner may have insufficient data samples to build an effective AI model. To this end, we propose a Federated Learning (FL) based privacy preserving approach to facilitate collaborative FL among multiple model owners in the IoV. Our system model enables collaborative model training without compromising data privacy given that only the model parameters instead of the raw data are exchanged within the federation. However, there are two main challenges of incentive mismatches between workers and model owners, as well as among model owners. For the former, we leverage on the self-revealing mechanism in contract theory under information asymmetry. For the latter, we use the coalitional game theory approach that rewards model owners based on their marginal contributions. The numerical results validate the performance efficiency of our proposed hierarchical incentive mechanism design.

Mobile data rewards is now leading a new economic trend in wireless networks, where the operators stimulate mobile users to view ads with data rewards and ask for corresponding payments from advertisers. Yet, due to the uncertain nature of users' preferences, it is always challenging for the advertiser to find the best choice of data rewards to attain an optimum balance between ad revenue and rewards spent. In this paper, we develop a general contract-theoretic framework to address the problem of data rewards design in a realistic asymmetric information scenario, where each user is associated with multidimensional private information. Specifically, we model the interplay between the advertiser and users by using a multidimensional contract design approach, and theoretically analyze optimal data rewarding schemes. To ensure global incentive compatibility, we convert the multi-dimensional contract problem into an equivalent one-dimensional contract problem. Necessary and sufficient conditions for an optimal and feasible contract are then derived to provide incentives for engagement of users in data rewarding scheme. We leverage numerical results to evaluate the performance of the designed multi-dimensional contract for data rewarding scheme.

In recent years, the enhanced sensing and computation capabilities of Internet-of-Things (IoT) devices have opened the doors to several mobile crowdsensing applications. In mobile crowdsensing, a model owner announces a sensing task following which interested workers collect the required data. However, in some cases, a model owner may have insufficient data samples to build an effective machine learning model. To this end, we propose a federated learning (FL)-based privacy-preserving approach to facilitate collaborative machine learning among multiple model owners in mobile crowdsensing. Our system model allows collaborative machine learning without compromising data privacy given that only the model parameters instead of the raw data are exchanged within the federation. However, there are two main challenges of incentive mismatches between workers and model owners, as well as among model owners. For the former, we leverage on the self-revealing mechanism in the contract theory under information asymmetry. For the latter, to ensure the stability of a federation through preventing free-riding attacks, we use the coalitional game theory approach that rewards model owners based on their marginal contributions. Considering the inherent hierarchical structure of the involved entities, we propose a hierarchical incentive mechanism framework. Using the backward induction, we first solve the contract formulation and then proceed to solve the coalitional game with the merge and split algorithm. The numerical results validate the performance efficiency of our proposed hierarchical incentive mechanism design, in terms of incentive compatibility of our contract design and fair payoffs of model owners in stable federation formation.