FedASMU: Efficient Asynchronous Federated Learning with Dynamic Staleness-Aware Model Update

Privacy-preserving Federated Learning (FL) based on Differential Privacy (DP) protects clients’ data by adding DP noise to samples’ gradients and has emerged as a de facto standard for data privacy in FL. However, the accuracy of global models in DP-based FL may be reduced significantly when rogue clients occur who deviate from the preset DP-based FL approaches and selfishly inject excessive DP noise beyond expectations, thereby applying a smaller privacy budget in the DP mechanism to ensure a higher level of security. Existing DP-based FL fails to prevent such attacks as they are imperceptible. Under the DP-based FL system and random Gaussian noise, the local model parameters of the rogue clients and the honest clients have identical distributions. In particular, the rogue local models show a low performance, but directly filtering out lower-performance local models compromises the generalizability of global models, as local models trained on scarce data also behave with low performance in the early epoch. In this paper, we propose ReFL, a novel privacy-preserving FL system that enforces DP and avoids the accuracy reduction of global models caused by excessive DP noise of rogue clients. Based on the observation that rogue local models with excessive DP noise and honest local models trained on scarce data have different performance patterns in long-term training epochs, we propose a long-term contribution incentives scheme to evaluate clients’ reputations and identify rogue clients. Furthermore, we design a reputation-based aggregation to avoid the damage of rogue clients’ models on the global model accuracy, based on the incentive reputation. Extensive experiments demonstrate ReFL guarantees the global model accuracy performance 0.77% - 81.71% higher than existing DP-based FL methods in the presence of rogue clients.

Federated learning (FL) is integral to advancing edge intelligence by enabling collaborative machine learning. In FL-empowered edge networks, computing nodes first train local models and then send them to an or multiple aggregation node(s) for global model collaboration. However, the trustworthiness of both local and global models in conventional FL frameworks is compromised due to inadequate model security and transparency. Distributed ledger technique (DLT) can address this issue by leveraging multi-nodes trust capabilities to support distributed consensus. However, model training and consensus performance of DLT may significantly degrade due to instability and resource constraints of edge networks. Sharding technique provides an effective approach by dividing the ledger into smaller and manageable shards. In this paper, to improve model training and consensus performance, we propose a trusted FL framework by incorporating sharding DLT into FL frameworks. We construct a theoretical model to investigate the relationship between model training performance, consensus efficiency, and capacity of edge nodes regarding storage, computing and communications. Based on the theoretical model, we propose a trusted clustering scheme to aggregate local models. Numerical results show that our proposed scheme significantly improves network throughput for transmitting models while guaranteeing model learning performance in comparison with some classical baselines.

Blockchain network (BCN)-based Self-Sovereign Identity (SSI) has emerged lately as an identity and access management framework that is based on Distributed Ledger Technology (DLT) and allows users to control their own data. Federated Learning (FL), on the other hand, provides a collaborative framework to update Machine Learning (ML) models without relying explicitly on data exchange between the users. This paper investigates identity management and authentication for vehicle users in the context of FL. We propose a novel approach based on blockchain-based SSI, which focuses on maintaining the authenticity and integrity of vehicle users’ identities and data exchanged between the users and the aggregation server during the execution of the FL iterations. A primary objective of this paper is to achieve shorter durations for credential operations in an FL setting as the system size scales out. Integrating BCN-based SSI into the FL framework addresses several critical FL challenges, ensuring enhanced system security and operational integrity. This synergy of BCN-based SSI with federated learning enables robust identity verification providing a solution to fundamental trustworthiness issues in FL without sacrificing the benefits of decentralized data control, improving both the performance and reliability of the FL system. Experimental results suggest that the proposed FL-based system, together with credential management on a blockchain platform, has the potential to significantly improve data integrity and ensure the authentication of users. More specifically, the results of the FL system demonstrate that it takes longer (on the order of a hundred seconds) as the number of rounds and clients increase, while the implemented Decentralized Identifier (DID) system relying on BCN-based SSI has dramatically shorter dedicated time for completing credential operations.

Federated Learning (FL) is considered the key, enabling approach for privacy-preserving, distributed machine learning (ML) systems. FL requires the periodic transmission of ML models from users to the server. Therefore, communication via resource-constrained networks is currently a fundamental bottleneck in FL, which is restricting the ML model complexity and user participation. One of the notable trends to reduce the communication cost of FL systems is gradient compression, in which techniques in the form of sparsification are utilized. However, these methods utilize a single compression rate for all users and do not consider communication heterogeneity in a real-world FL system. Therefore, these methods are bottlenecked by the worst communication capacity across users. Further, sparsification methods are non-adaptive and do not utilize the redundant, similar information across users' ML models for compression. In this paper, we introduce a novel Dynamic Sparsification for Federated Learning (DSFL) approach that enables users to compress their local models based on their communication capacity at each iteration by using two novel sparsification methods: layer-wise similarity sparsification (LSS) and extended top- <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$K$</tex> sparsification. LSS enables DSFL to utilize the global redundant information in users' models by using the Centralized Kernel Alignment (CKA) similarity for sparsification. The extended top- <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$K$</tex> model sparsification method empowers DSFL to accommodate the heterogeneous communication capacity of user devices by allowing different values of sparsification rate <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$K$</tex> for each user at each iteration. Our extensive experimental results <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> All code and experiments are publicly available at: https://github.com/mahdibeit/DSFL. on three datasets show that DSFL has a faster convergence rate than fixed sparsification, and as the communication heterogeneity increases, this gap increases. Further, our thorough experimental investigations uncover the similarities of user models across the FL system.

In the era of computational social systems (CSS), where AI is increasingly embedded in critical domains such as public services, healthcare, and social governance, concerns about system vulnerabilities have become paramount. Federated learning (FL) offers a promising solution by enabling privacy-preserving and secure AI model training in real-world applications. However, traditional FL approaches often assume that client data is either imbalanced or non-independent and identically distributed (non-IID), whereas in practice, these issues frequently coexist. In such complex scenarios, minority classes may appear only on a small subset of clients, significantly degrading global model performance and convergence. In this article, we propose a novel FL framework designed to tackle the intertwined challenges of data imbalance and non-IID data by a principled, decoupled approach. Unlike existing methods that address these issues in isolation, our approach introduces three synergistic innovations, each operating at a different level of the FL system. At the data level, a global rebalancing mechanism employs a privacy-preserving modified Z-score to rectify class imbalance. At the client level, a distribution-aware clustering strategy groups participants based on data subspace similarity. At the feature level, a novel contrastive loss function, leveraging the effective number of samples, simultaneously mitigates local imbalance and model drift. This cohesive framework ensures that interventions at each level reinforce each other, leading to robust performance. Extensive experiments show that FedScFc outperforms state-of-the-art baselines.

The convergence of vehicular technology, artificial intelligence (AI), and distributed computing has catalyzed the emergence of the Internet of Vehicles (IoV) as a cornerstone of next-generation intelligent transportation systems (ITS). By enabling vehicle-to-everything (V2X) communication, IoV supports cooperative perception, real-time decision-making, and autonomous driving. However, the reliance on large-scale, data-driven intelligence in IoV exposes systems to critical challenges, including adversarial poisoning, privacy leakage, identity forgery, and the fragility of centralized learning architectures. Federated Learning (FL) has been proposed as a promising paradigm to alleviate some of these issues by enabling distributed model training without centralizing sensitive vehicular data. Nonetheless, conventional FL remains vulnerable to security and trust limitations, particularly in dynamic vehicular environments. This thesis addresses these challenges by designing secure, privacy-preserving, and scalable FL frameworks that leverage distributed ledger technologies and cutting-edge security mechanisms.The thesis advances knowledge through four interconnected contributions. First, two novel optimization-driven poisoning attack models are introduced: PA-PSOSA and PAPSOGA, which combine particle swarm optimization with simulated annealing and genetic algorithms, respectively. These models demonstrate that even a small poisoning budget can substantially degrade global model utility under black-box and clean-label constraints, highlighting the urgency of robust defenses in vehicular FL. Second, a permissioned blockchain-enabled FL (BCFL) framework is proposed, in which consortium edge nodes running Practical Byzantine Fault Tolerance (PBFT) consensus replace the central aggregator. With blockchain integration and data validation mechanisms, this design ensures identity authentication, verifiable audit trails, and improved resilience against poisoning and Sybil attacks, while maintaining high model accuracy under adversarial conditions. Third, the framework is further enhanced to achieve inference-resistance by integrating secure aggregation (SecAgg) and differential privacy (DP), and lightweight with off-chain commitments. This design significantly reduces ledger storage requirements, increases system throughput, and mitigates inference-based privacy risks. Finally, to overcome the scalability limitations of PBFT-based BCFL, a DAG-enabled FL (DFL) framework is developed. By leveraging parallel validation, utility-score-based tip selection, and reputation-weighted aggregation, this framework significantly improves scalability, reduces communication complexity, and enhances robustness in asynchronous vehicular environments.Together, these contributions articulate a coherent progression from exposing vulnerabilities in vehicular FL to constructing secure, privacy-preserving, and scalable frameworks tailored for IoV ecosystems. The findings demonstrate that interdisciplinary integration of optimization theory, cryptography, differential privacy, and distributed ledger technologies is indispensable for trustworthy vehicular intelligence. Beyond theoretical significance, the proposed frameworks offer practical designs for deployment in safety-critical IoV environments. Future research directions include the integration of zero-knowledge proofs (ZKP) for verifiable privacy, adaptive defenses against evolving adversarial strategies, and experimental validation in real-world vehicular testbeds. Collectively, this thesis establishes a foundation for secure federated intelligence in IoV, contributing to the reliability, efficiency, and trustworthiness of next-generation ITS.

In this paper, the convergence time of federated learning (FL), when deployed over a realistic wireless network, is studied. In particular, a wireless network is considered in which wireless users transmit their local FL models (trained using their locally collected data) to a base station (BS). The BS, acting as a central controller, generates a global FL model using the received local FL models and broadcasts it back to all users. Due to the limited number of resource blocks (RBs) in a wireless network, only a subset of users can be selected to transmit their local FL model parameters to the BS at each learning step. Moreover, since each user has unique training data samples, the BS prefers to include all local user FL models to generate a converged global FL model. Hence, the FL training loss and convergence time will be significantly affected by the user selection scheme. Therefore, it is necessary to design an appropriate user selection scheme that can select the users who can contribute toward improving the FL convergence speed more frequently. This joint learning, wireless resource allocation, and user selection problem is formulated as an optimization problem whose goal is to minimize the FL convergence time and the FL training loss. To solve this problem, a probabilistic user selection scheme is proposed such that the BS is connected to the users whose local FL models have significant effects on the global FL model with high probabilities. Given the user selection policy, the uplink RB allocation can be determined. To further reduce the FL convergence time, artificial neural networks (ANNs) are used to estimate the local FL models of the users that are not allocated any RBs for local FL model transmission at each given learning step, which enables the BS to improve the global model, the FL convergence speed, and the training loss. Simulation results show that the proposed approach can reduce the FL convergence time by up to 56% and improve the accuracy of identifying handwritten digits by up to 3%, compared to a standard FL algorithm.

A large number of mobile devices, smart wearable devices, and medical and health sensors continue to generate massive amounts of data, making edge devices’ data explode and making it possible to implement data-driven artificial intelligence. However, the “data silos” and other issues still exist and need to be solved. Fortunately, federated learning (FL) can deal with “data silos” in the medical field, facilitating collaborative learning across multiple institutions without sharing local data and avoiding user concerns about data privacy. However, it encounters two main challenges in the medical field. One is statistical heterogeneity, also known as non-IID (non-independent and identically distributed) data, i.e., data being non-IID between clients, which leads to model drift. The second is limited labeling because labels are hard to obtain due to the high cost and expertise requirement. Most existing federated learning algorithms only allow for supervised training settings. In this work, we proposed a novel federated learning framework, MixFedGAN, to tackle the above issues in federated networks with dynamic aggregation and knowledge distillation. A dynamic aggregation scheme was designed to reduce the impact of current low-performing clients and improve stability. Knowledge distillation was introduced into the local generator model with a new distillation regularization loss function to prevent essential parameters of the global generator model from significantly changing. In addition, we considered two scenarios under this framework: complete annotated data and limited labeled data. An experimental analysis on four heterogeneous COVID-19 infection segmentation datasets and three heterogeneous prostate MRI segmentation datasets verified the effectiveness of the proposed federated learning method.

Additive manufacturing (AM) enables the production of customized and complex metal parts, providing greater flexibility than traditional mass production. However, maintaining consistent product quality for AM processes remains challenging due to process variability and heat emission fluctuations, which can cause defects such as overheating. Overheating occurs when non-uniform temperature distributes across the printed parts, leading to issues such as structural weaknesses. Predicting heat emissions accurately is essential to preventing such issues, but AM facilities, particularly small- and medium-sized enterprises (SMEs), generate limited and heterogeneous datasets due to unique configurations and privacy concerns, making traditional centralized predictive model training paradigms impractical. Federated learning (FL) offers a privacy-preserving solution, it alleviates data privacy and data scarcity concerns by enabling collaborative learning across decentralized datasets while keeping data local. However, its performance suffers under heterogeneous client data and varied computational resources. This creates a need to address data heterogeneity while maintaining both global model performance and individual client personalization. We propose FedScope-KD, a novel heterogeneity-aware FL framework designed to balance the scope of global and personalized learning. Client heterogeneity level is quantified prior to the FL training, to improve the model weight aggregation during training. This is achieved through component decomposition and knowledge distillation. The framework decomposes client data into process-invariant representations, which capture the fundamental nature of the laser powder bed fusion (LPBF) process, and process-variant representations, which reflect local, client-specific configuration settings. This decomposition ensures that global models benefit from collaborative learning on the homogeneous data representations, while personalized predictions remain tailored to client-specific heterogeneous data representations. A knowledge distillation (KD) mechanism further enhances the framework by efficiently transferring process-invariant knowledge from a global teacher model to local student models. We compare the heterogeneity index generation and calculate the Dynamic Time Warping (DTW) distance for both inter-client variant and invariant components. The variant components exhibit greater distances between clients, reflecting their inherent heterogeneity, while the invariant components are more closely aligned across clients. This pattern demonstrates the effectiveness of the decomposition process in separating heterogeneous and homogeneous information. The heterogeneity index is further used for weight aggregation during FL training. The framework’s performance is validated through a comparison with baseline FL methods such as FedAvg, as well as centralized and individual learning paradigms. Performance metrics include personalized performance and global accuracy with MSE. Through experiments on heat emission datasets in the LPBF process, we show that FedScope-KD successfully addresses the challenges of data heterogeneity and resource constraints, providing a robust solution of predictive modeling for SMEs.

Federated learning (FL) offers an effective learning architecture to protect data privacy in a distributed manner. However, the inevitable network asynchrony, overdependence on a central coordinator, and lack of an open and fair incentive mechanism collectively hinder FL's further development. We propose IronForge, a new generation of FL framework, that features a directed acyclic graph (DAG)-based structure, where nodes represent uploaded models, and referencing relationships between models form the DAG that guides the aggregation process. This design eliminates the need for central coordinators to achieve fully decentralized operations. IronForge runs in a public and open network and launches a fair incentive mechanism by enabling state consistency in the DAG. Hence, the system fits in networks where training resources are unevenly distributed. In addition, dedicated defense strategies against prevalent FL attacks on incentive fairness and data privacy are presented to ensure the security of IronForge. Experimental results based on a newly developed test bed FLSim highlight the superiority of IronForge to the existing prevalent FL frameworks under various specifications in performance, fairness, and security. To the best of our knowledge, IronForge is the first secure and fully decentralized FL (DFL) framework that can be applied in open networks with realistic network and training settings.

Federated learning (FL) is an emerging machine learning paradigm. With FL, distributed data owners aggregate their model updates to train a shared deep neural network collaboratively, while keeping the training data locally. However, FL has little control over the local data and the training process. Therefore, it is susceptible to poisoning attacks, in which malicious or compromised clients use malicious training data or local updates as the attack vector to poison the trained global model. Moreover, the performance of existing detection and defense mechanisms drops significantly in a scaled-up FL system with non-iid data distributions. In this paper, we propose a defense scheme named CONTRA to defend against poisoning attacks, e.g., label-flipping and backdoor attacks, in FL systems. CONTRA implements a cosine-similarity-based measure to determine the credibility of local model parameters in each round and a reputation scheme to dynamically promote or penalize individual clients based on their per-round and historical contributions to the global model. With extensive experiments, we show that CONTRA significantly reduces the attack success rate while achieving high accuracy with the global model. Compared with a state-of-the-art (SOTA) defense, CONTRA reduces the attack success rate by 70% and reduces the global model performance degradation by 50%.

With the growth of participating clients, the centralized parameter server (PS) will seriously limit the scale and efficiency of Federated Learning (FL). A straightforward approach to scale up the FL system is to construct a Parallel FL (PFL) system with multiple parallel PSes. However, it is unclear whether PFL can really accelerate FL or reduce the training time of FL. Even if the answer is yes, it is non-trivial to design a highly efficient parameter average algorithm for a PFL system. In this paper, we propose a completely parallelizable FL algorithm called P-FedAvg under the PFL architecture. P-FedAvg extends the well-known FedAvg algorithm by allowing multiple PSes to cooperate and train a learning model together. In P-FedAvg, each PS is only responsible for a fraction of total clients, but PSes can mix model parameters in a dedicatedly designed way so that the FL model can well converge. Different from heuristic-based algorithms, P-FedAvg is with theoretical guarantees. To be rigorous, we theoretically analyze the convergence rate of P-FedAvg in terms of the number of conducted iterations, the communication cost of each global iteration and the optimal weights for each PS to mix parameters with its neighbors. Based on theoretical analysis, we conduct a case study on five typical overlay topolgoies formed by PSes to further examine the communication efficiency under different topologies, and investigate how the overlay topology affects the convergence rate, communication cost and robustness of a PFL system. Lastly, we perform extensive experiments with real datasets to verify our analysis and demonstrate that P-FedAvg can significantly speed up FL than traditional FedAvg and other competitive baselines. We believe that our work can help to lay a theoretical foundation for building more efficient PFL systems.

Hot water demand forecasting is crucial for estimating aggregated flexibility from distributed electric water heaters (EWHs). High-performance deep learning models for forecasting require large amounts of training data that may not be available to aggregators. Privacy preserving edge learning methods for individual EWHs cannot learn from other EWHs. To address these challenges, this paper proposes a federated learning (FL) framework for hot water demand class forecasting across multiple distributed EWHs with limited demand data. Feed-forward neural network (FNN) based global model is collaboratively trained by multiple edge devices without sharing data to predict hot water demand. The global model is specifically further fine-tuned to individual EWHs using their own data. The proposed approach is tested with synthetic hot water demand data from 40 households and the results indicate that the proposed FL framework can perform better than edge learning and has numerous other advantages.

Federated learning (FL) has attracted tremendous attentions in recent years due to its privacy-preserving measures and great potential in some distributed but privacy-sensitive applications, such as finance and health. However, high communication overloads for transmitting high-dimensional networks and extra security masks remain a bottleneck of FL. This article proposes a communication-efficient FL framework with an Adaptive Quantized Gradient (AQG), which adaptively adjusts the quantization level based on a local gradient’s update to fully utilize the heterogeneity of local data distribution for reducing unnecessary transmissions. In addition, client dropout issues are taken into account and an Augmented AQG is developed, which could limit the dropout noise with an appropriate amplification mechanism for transmitted gradients. Theoretical analysis and experiment results show that the proposed AQG leads to 18% to 50% of additional transmission reduction as compared with existing popular methods, including Quantized Gradient Descent (QGD) and Lazily Aggregated Quantized (LAQ) gradient-based methods without deteriorating convergence properties. Experiments with heterogenous data distributions corroborate a more significant transmission reduction compared with independent identical data distributions. The proposed AQG is robust to a client dropping rate up to 90% empirically, and the Augmented AQG manages to further improve the FL system’s communication efficiency with the presence of moderate-scale client dropouts commonly seen in practical FL scenarios.

Federated learning (FL) empowers a cohort of participating devices to contribute collaboratively to a global neural network model, ensuring that their training data remains private and stored locally. Despite its advantages in computational efficiency and privacy preservation, FL grapples with the challenge of non-IID (not independent and identically distributed) data from diverse clients, leading to discrepancies between local and global models and potential performance degradation. In this article, we propose FedGK, an innovative communication-efficient Group-Guided FL framework designed for heterogeneous data distributions. FedGK employs a localized-guided framework that enables the client to effectively assimilate key knowledge from teachers and peers while minimizing extraneous peer information in FL scenarios. We conduct an in-depth analysis of the dynamic similarities among clients over successive communication rounds and develop a novel clustering approach that accurately groups clients with diverse heterogeneities. We implement FedGK on public datasets with an innovative data transformation pattern called “cluster-shift non-IID”, which mirrors the more prevalent data distributions in real-world settings and could be grouped into clusters with similar data distributions. Extensive experimental results on public datasets demonstrate that the proposed approach FedGK improves accuracy by up to 32.89% and saves up to 53.33% communication cost over state-of-the-art baselines.