Federated Learning Research Articles

Unifying domain gap in Federated Learning: A geometric approach

Federated Learning (FL) is a framework designed to enable distributed and privacy-preserving learning. It typically involves a central server coordinating multiple clients to collaboratively train a global model without the need for sharing private data. Recent studies have revealed that this parameter-only communication strategy can be hindered by non-independent and identically distributed (non-iid) data across clients, leading to statistical heterogeneity. This issue necessitates the development of Personalized Federated Learning (PFL), which aims to enhance the performance of individual clients while still allowing for the learning of a global model. Most existing work on PFL has focused on label shift in supervised tasks, with relatively little attention given to feature shift, another common problem in real-world applications of federated learning. For instance, client data may vary in terms of illumination, angles, and quality for natural images, or in imaging protocols for medical images. To address this issue, we propose a general yet powerful framework that leverages the geometric interpretation of deep neural networks. Geometrically, a deep neural network partitions the feature space into a Power Diagram (PD) or Voronoi Diagram (VD). Regularized losses are introduced to mitigate feature shift from the perspective of PD and VD. Additionally, a personalized generator network is formulated for each client to rectify feature distribution and adapt the input data from its own domain to an ”averaged” or unified domain that generalizes well across all clients. Our method demonstrates competitive performance compared to current state-of-the-art methods.

BADFL: Backdoor Attack Defense in Federated Learning From Local Model Perspective

BADFL: Backdoor Attack Defense in Federated Learning From Local Model Perspective

FedGen: Personalized federated learning with data generation for enhanced model customization and class imbalance

Federated learning has emerged as a prominent solution for the collaborative training of machine learning models without exchanging local data. However, existing approaches often impose rigid constraints on model heterogeneity, limiting the ability of clients to customize unique models and increasing the vulnerability of models to potential attacks. This paper presents FedGen, a novel personalized federated learning framework based on generative adversarial networks (GANs). FedGen shifts the focus from training task-specific models to generating data, especially for minority classes with imbalanced data. With FedGen, clients can gain knowledge from others by training generators, while maintaining a heterogeneous local model and avoiding sharing model information with other participants. Moreover, to address challenges arising from imbalanced data, we propose AT-GAN, a novel generative model incorporating pseudo augmentation and differentiable augmentation modules to foster healthy competition between the generator and discriminator. To evaluate the effectiveness of our approach, we conduct extensive experiments on real-world tabular datasets. The experimental results demonstrate that FedGen significantly enhances the performance of local models, achieving improvements of up to 11.92% in F1 score and up to 9.14% in MCC score compared to existing methods.

Trusted Model Aggregation With Zero-Knowledge Proofs in Federated Learning

Trusted Model Aggregation With Zero-Knowledge Proofs in Federated Learning

Securing IoMT Healthcare Systems with Federated Learning and BigchainDB

Securing IoMT Healthcare Systems with Federated Learning and BigchainDB

Hierarchical Federated Deep Reinforcement Learning based Joint Communication and Computation for UAV Situation Awareness

The computation-intensive situational awareness (SA) task of unmanned aerial vehicle (UAV) is greatly affected by its limited power and computing capability. To solve this challenge, we consider the joint communication and computation (JCC) design for UAV network in this paper. Firstly, a multi-objective optimization (MOO) model, which can optimize UAV computation offloading, transmit power, and local computation resources simultaneously, is built to minimize energy consumption and task execution delay. Then, we develop Thompson sampling based double-DQN (TDDQN) learning algorithm which allows the agent to explore more deeply and effectively, and propose a joint optimization algorithm that combines TDDQN and sequential least squares quadratic programming (SLSQP) to handle the MOO problem. Finally, to enhance the training speed and quality, we incorporate federated learning (FL) into the presented joint optimization algorithm and propose hierarchical federated TDDQN with SLSQP (HF TDDQN-S) to implement the JCC design. Simulation results show that the introduced HF TDDQN-S can efficiently learn the best JCC strategy and minimize the average cost contrasted with the DDQN with SLSQP (DDQN-S) and TDDQN with SLSPQ (TDDQN-S) approach, and achieve the low average delay SA with power efficient.

Distributed Rumor Source Detection via Boosted Federated Learning

Distributed Rumor Source Detection via Boosted Federated Learning

Federated Learning for Personalized Financial Recommendations

Abstract: Federated Learning (FL) has been the solution to one of those biggest contributors that have scared us from using Machine learning, i.e. Privacy [ for sensitive domains like finance ]. This survey focuses on leveraging Federated Learning in creating personalized recommendation systems for financial products such as loans, investment plans, credit cards and savings. For example, classical recommendation systems usually work in a centralized way to store a lot of sensitive financial data (or derivative structures), this setting presents other well-known privacy issues and security risks. FL provides a solution that enables multiple financial institutions to work together to train a global recommendation model without the need any of them to share their raw customer data. The paper reviews federated learning, and some key take ways are on differential privacy and secure aggregation to protect customer data while improving the quality of recommendations. We also talk about how to solve some problems like heterogeneity of the data, model convergence and regulatory constraints required in financial methods. The paper concludes by detailing future directions for federated learning in finance, with focus on how personalized financial recommendations can be dramatically transformed while preserving user privacy.

Integration of Foundation Models and Federated Learning in AIoT-Based Aircraft Health Monitoring Systems

The study presents a comprehensive framework for integrating foundation models (FMs), federated learning (FL), and Artificial Intelligence of Things (AIoT) technologies to enhance aircraft health monitoring systems (AHMSs). The proposed architecture uses the strengths of both centralized and decentralized learning approaches, combining the broad knowledge capture of foundation models with the privacy-preserving and adaptive nature of federated learning. Through extensive simulations on a representative aircraft fleet, the integrated FM + FL approach demonstrated consistently superior performance compared to standalone implementations across multiple key metrics, including prediction accuracy, model size efficiency, and convergence speed. The framework establishes a robust digital twin ecosystem for real-time monitoring, predictive maintenance, and fleet-wide optimization. Comparative analysis reveals significant improvements in anomaly detection capabilities and reduced false alarm rates compared to traditional methods. The study conducts a systematic evaluation of the benefits and limitations of FM, FL, and integrated approaches in AHMS, examining their implications for system robustness, scalability, and security. Statistical analysis confirms that the integrated approach substantially enhances precision and recall in identifying potential failures while optimizing computational resources and training time. This paper outlines a detailed aviation ecosystem architecture integrating these advanced AI technologies across centralized processing, client, and communication domains. Future research directions are identified, focusing on improving model efficiency, ensuring generalization across diverse operational conditions, and addressing regulatory and ethical considerations.

Privacy preserving verifiable federated learning scheme using blockchain and homomorphic encryption

This paper introduces a novel Privacy-Preserving Verifiable Federated Learning (PPVFL) scheme that integrates blockchain technology and homomorphic encryption to address critical challenges in decentralized machine learning. The proposed scheme ensures data privacy, integrity, verifiability, robust security, and efficiency in collaborative learning environments, particularly in sensitive domains such as healthcare. By leveraging blockchain’s decentralized, immutable ledger and homomorphic encryption’s capability to perform computations on encrypted data, the model maintains the confidentiality of sensitive information throughout the learning process. The inclusion of Byzantine fault tolerance and Elliptic Curve Digital Signature Algorithm (ECDSA) further enhances the system’s security against malicious attacks and data tampering, while the optimization of computational processes ensures efficient model training and communication. The novelty of this work lies in the seamless integration of blockchain and homomorphic encryption within a federated learning framework, specifically tailored for post-quantum cryptography, a combination that has not been extensively explored in prior research. This research represents a significant advancement in secure and efficient federated learning, offering a promising solution for industries that prioritize data privacy, security, and trust in collaborative machine learning. The effectiveness, security, and efficiency of the PPVFL scheme were validated using the Glaucoma dataset. The proposed method outperformed baseline federated learning algorithms, achieving a Dice coefficient of 0.918 and a Hausdorff distance of 4.05 on Severe Glaucoma (SG) cases, compared to 0.905 and 5.27, respectively, with traditional FedAvg. Moreover, the integration of blockchain and homomorphic encryption ensured that data privacy was upheld without compromising model performance, while efficient computation and communication processes minimized latency and resource consumption. This study contributes a robust, privacy-preserving, secure, efficient, and verifiable federated learning framework that addresses the pressing need for secure and scalable data management in distributed machine learning environments.

Federated learning-based wavelength demodulation system for multi-point distributed multi-peak FBG sensors

Machine learning-based demodulation of multi-peak fiber Bragg grating (FBG) sensors has been extensively studied, demonstrating superior performance compared to conventional algorithms because it can neglect potential physical constraints. As the number of real-world monitoring points increases, the volume of fiber-optic sensing data grows exponentially. This necessitates aggregating data from various regions (e.g., via Wi-Fi), unlike traditional single-point monitoring, which challenges server storage capacity and communication efficiency. To address these issues, this paper proposes a federated learning (FL)-based framework for efficient wavelength demodulation of multi-peak FBGs in multipoint monitoring. Specifically, an arrayed waveguide grating (AWG) with multiplexing capability is employed at different monitoring points to convert spectral features into multi-channel transmission intensities, serving as training data for local models. Subsequently, the local model parameters, trained independently at each point, are uploaded to a central server to derive the optimal global model for demodulation across different monitoring points. The proposed demodulation framework is validated through stress demodulation experiments on multi-peak FBG sensors. Experimental results indicate strong multi-peak extraction performance with a demodulation error of ±0.64 pm. Additionally, the method demonstrates excellent applicability for generating high-precision global demodulation models through multi-node cooperative work under various scenarios.

Enhancing federated learning with dynamic weight adjustment based on particle swarm optimization

Federated learning (FL) stands as a promising distributed machine learning approach today, allowing model training on local clients without data sharing. However, varied contributions among clients often impact the global model’s performance, while FL confronts challenges like communication overhead, data heterogeneity, and privacy concerns. In this paper, we introduce a novel federated learning server aggregation algorithm: the Federated Learning Algorithm with Optimized Weight Aggregation via Particle Swarm Optimization Algorithm (AdpFedPSO). This approach dynamically adjusts client model contribution weights based on their performance and stability, aiming to enhance global model accuracy, convergence speed, and make model aggregation smarter and more adaptable. Through experimental validation on real datasets, we find that AdpFedPSO enhances accuracy by about 15% on the 0.6-Dirichlet MNIST dataset, 7.3% on the FashionMNIST dataset, and 13.4% on the CIFAR-10 dataset compared to the traditional FL aggregation method, FedAvg. These results indicate that AdpFedPSO not only enhances the accuracy of the global model but also expedites the model’s convergence speed. Additionally, it demonstrates resilience across various levels of client numbers, participation rates, and client heterogeneity, providing valuable reference and guidance for the further development of FL technology. Moreover, the concept of employing the particle swarm optimization algorithm for FL model aggregation also offers new insights and directions for future research.

Privacy-preserving MTS anomaly detection for network devices through federated learning

In the context of Maintenance-as-a-Service (MaaS), it is important for device vendors to develop multivariate time series (MTS) anomaly detection models that can accurately identify anomalies without compromising the privacy of customer enterprises' data. In this paper, we investigate the relationship between MTS data patterns and the parameters of unsupervised autoencoder (AE) models and show that they are highly consistent. Building on this insight, we propose a novel unsupervised federated learning (FL)-based framework called OmniFed, which cannot only address the heterogeneity of non-independent identically (non-iid) distributed data on different devices, but also achieve high-precision detection of device MTS anomalies while ensuring privacy. Specifically, OmniFed is initialized with an AE model and then trains local AE models on individual devices via federated learning. Finally, OmniFed clusters devices based on the parameters of the AE models and trains a cluster-specific MTS anomaly detection model using FL. Our experiments on two real-world datasets demonstrate that OmniFed achieves an F1-Score of 0.921, significantly higher than the best baseline method.

MatSwarm: trusted swarm transfer learning driven materials computation for secure big data sharing

The rapid advancement of Industry 4.0 necessitates close collaboration among material research institutions to accelerate the development of novel materials. However, multi-institutional cooperation faces significant challenges in protecting sensitive data, leading to data silos. Additionally, the heterogeneous and non-independent and identically distributed (non-i.i.d.) nature of material data hinders model accuracy and generalization in collaborative computing. In this paper, we introduce the MatSwarm framework, built on swarm learning, which integrates federated learning with blockchain technology. MatSwarm features two key innovations: a swarm transfer learning method with a regularization term to enhance the alignment of local model parameters, and the use of Trusted Execution Environments (TEE) with Intel SGX for heightened security. These advancements significantly enhance accuracy, generalization, and ensure data confidentiality throughout the model training and aggregation processes. Implemented within the National Material Data Management and Services (NMDMS) platform, MatSwarm has successfully aggregated over 14 million material data entries from more than thirty research institutions across China. The framework has demonstrated superior accuracy and generalization compared to models trained independently by individual institutions.

Federated Learning-Based Traffic Flow Prediction Model in Intelligent Transportation Systems

The existing Intelligent Transportation System (ITS) achieves high success. As an essential component of ITS, Traffic Flow Prediction (TFP) has attracted tremendous attention. It is a critical but challenging task to improve the robust convergence and high accuracy of TFP in real-world scenarios. This study presents an optimized Federated Learning (FL)-based ChebNet model, FedproxChebNet, to realize the highly effective and accurate TFP. By selecting the best penalty constant in the proximal term to optimize the objective function, this model can achieve fast and stable convergence. Using the ChebNet model to aggregate neighbor nodes’ characteristics, more hidden information underlying the spatio-temporal traffic data can be taken into consideration for training the global and local models. All the superiority of the FedproxChebNet model makes it outperform other FL models with the Graph Convolutional Network (GCN), Graph Attention Network (GAT) and Spatio-Temporal Graph Convolutional Network (STGCN). We designed a series of experiments on various FL-based GNN model comparisons, parameter sensitivity tests, and on verifying the performance of FedproxChebNet with different heterogeneous systems with [Formula: see text], [Formula: see text] and [Formula: see text]. Based on four real-world data sets from the cognitive network, the experimental results demonstrate that the presented FedproxChebNet provides the best convergence and the highest accuracy in TFP, and achieves the best performance in a highly heterogeneous system ([Formula: see text]). Specifically, the accuracy of FedproxChebNet is at least improved by [Formula: see text] on PeMS07 than other FL-based GNN models. This proposed FedproxChebNet model may be preferable for different scenarios in ITS such as route planning, traffic congestion control and reversible lanes.

Real-world federated learning in radiology: hurdles to overcome and benefits to gain.

Federated Learning (FL) enables collaborative model training while keeping data locally. Currently, most FL studies in radiology are conducted in simulated environments due to numerous hurdles impeding its translation into practice. The few existing real-world FL initiatives rarely communicate specific measures taken to overcome these hurdles. To bridge this significant knowledge gap, we propose a comprehensive guide for real-world FL in radiology. Minding efforts to implement real-world FL, there is a lack of comprehensive assessments comparing FL to less complex alternatives in challenging real-world settings, which we address through extensive benchmarking. We developed our own FL infrastructure within the German Radiological Cooperative Network (RACOON) and demonstrated its functionality by training FL models on lung pathology segmentation tasks across six university hospitals. Insights gained while establishing our FL initiative and running the extensive benchmark experiments were compiled and categorized into the guide. The proposed guide outlines essential steps, identified hurdles, and implemented solutions for establishing successful FL initiatives conducting real-world experiments. Our experimental results prove the practical relevance of our guide and show that FL outperforms less complex alternatives in all evaluation scenarios. Our findings justify the efforts required to translate FL into real-world applications by demonstrating advantageous performance over alternative approaches. Additionally, they emphasize the importance of strategic organization, robust management of distributed data and infrastructure in real-world settings. With the proposed guide, we are aiming to aid future FL researchers in circumventing pitfalls and accelerating translation of FL into radiological applications.

Taxonomy and Survey of Collaborative Intrusion Detection System using Federated Learning

This review paper looks at recent research on Federated Learning (FL) for Collaborative Intrusion Detection Systems (CIDS) to establish a taxonomy and survey. The motivation behind this review comes from the difficulty of detecting coordinated cyberattacks in large-scale distributed networks. Collaborative anomalies are one of the network anomalies that need to be detected through robust collaborative learning methods. FL is promising collaborative learning method in recent research. This review aims to offer insights and lesson learn for creating a taxonomy of collaborative anomaly detection in CIDS using FL as a collaborative learning method. Our findings suggest that a taxonomy is required to map the discussion area, including an algorithm for training the learning model, the dataset, global aggregation model, system architecture, security, and privacy. Our results indicate that FL is a promising approach for collaborative anomaly detection in CIDS, and the proposed taxonomy could be useful for future research in this area. Overall, this review contributes to the growing knowledge of FL for CIDS, providing insights and lessons for researchers and practitioners. This research also concludes significant challenges, opportunities, and future directions in CIDS based on collaborative anomaly detection using FL.

FL-APB: Balancing Privacy Protection and Performance Optimization for Adversarial Training in Federated Learning

Federated Learning (FL), as a distributed machine learning method, is particularly suitable for training models that require large amounts of data while meeting increasingly strict data privacy and security requirements. Although FL effectively protects the privacy of participants by avoiding the sharing of raw data, balancing the risks of privacy leakage with model performance remains a significant challenge. To address this, this paper proposes a new algorithm—FL-APB (Federated Learning with Adversarial Privacy–Performance Balancing). This algorithm combines adversarial training with privacy-protection mechanisms to dynamically adjust privacy and performance budgets, optimizing the balance between the two while enhancing and ensuring performance. The experimental results demonstrate that the FL-APB algorithm significantly improves model performance across various adversarial training scenarios, while effectively protecting the privacy of participants through adversarial training of privacy data.

A privacy-preserving federated learning approach for airline upgrade optimization

PurposeA key issue of making upgrade decisions is to match the most relevant upgrade offers to the right customers at the right time. To optimize upgrade strategies and profitability, companies seek to break “data silos” between themselves and other business partners for a more holistic view of customers' consumption experiences. However, multi-source data fusion may lead to potential privacy leakage. To overcome these two challenges in data silos and privacy protection, this study introduced a privacy-preserving federated learning (FL) approach and explained the process of using FL in modeling airline passengers’ willingness to pay for upgrade offers. Design/methodology/approachFederated learning is a new confidential computing technique that allows companies to train a model cooperatively by exchanging model parameters instead of the actual raw data, which might include customers' privacy sensitive information. Using a case study of a Chinese airline company, this study demonstrated how FL-based upgrade models using multi-source data can be developed to improve the accuracy of predicting customers' willingness to pay for upgrades while preserving customers’ personal data privacy. FindingsComparing with traditional unilateral model using single-source data, the federated logistic regression and SecureBoost models demonstrate better model performance. This indicates that the proposed FL approach can enhance the accuracy of modeling airline passengers' willingness to pay for upgrade offers while preserving passengers’ data privacy. The findings also show that the FL-based models generally took longer running time than the traditional unilateral model due to the design of FL approach in ensuring data privacy. OriginalityThis study contributes to the literature of upgrade optimization by introducing the new FL approach for developing machining learning models to predict customers’ reaction to upgrade offers. Although we focus on the airline industry in our case study, the proposed FL approach can be applied to other industries with a similar issue of upgrade optimization such as hotels or cruise lines, and car rental.

Federated learning system on autonomous vehicles for lane segmentation

Autonomous Vehicles (AV) is one of the most evolving industries in the last decade. However, one of the bottlenecks of this evolution is providing data that contains different scenarios and scenes to improve the models without exposing the privacy and security of the edge vehicles. The authors of this research propose a secure and efficient novel solution for lane segmentation in AVs through the use of Federated Learning (FL). FedLane involves initial training of U-Net, ResUNet, and ResUNet++ models, followed by real-time inference in edge devices and the application of FL to update the server model using clients’ data. The study found that FL has enhanced the performance of lane segmentation significantly over baseline, enabling decentralized privacy-preserving collaborative optimization with increased dice coef from 0.9429 to 0.9794 for U-Net, from 0.9291 to 0.9854 for ResUNet and from 0.9079 to 0.9675 for ResUNet++. Additionally, the models show increased stability over the training iterations, highlighting the potential of FL to play a significant role in the future of automation in the AV industry.