Federated Learning Model Research Articles

Problems, solutions and improvements on federated learning model

The field of machine learning has been stepping forward at a significant pace since the 21century due to the continuous modifications and improvements on the major underlying algorithms, particularly the model named federated learning (FL). This paper will specifically focus on the Partially Distributed and Coordinated Model, one of the major models subject to federated learning, to provide an analysis of the models working algorithms, existing problems and solutions, and improvements on the original model. The identification of the merits and drawbacks of each solution will be founded on document analysis, data analysis and contrastive analysis. The research concluded that both alternative solutions and improvements to the original model can possess their unique advantage as well as newly-emerged concerns or challenges.

RETRACTED ARTICLE: Optimized design and application research of smart interactive screen for wireless networks based on federated learning

The rapid development of infinite networks and information technology has promoted the wide deployment and rapid growth of intelligent interactive devices. However, at the same time, touch interaction technology also faces many challenges such as lack of precision. This study combines federated learning with LayerGesture technology to optimize and design a touch interaction system with higher interaction accuracy and applies it to practice. The analysis results show that with the increase in the number of iterations of the federated model, the accuracy of the human–computer recognition interaction and the amount of information contained in it increases, and the accuracy curve reaches stability at about 2800 times and is at the optimal interaction adaptation. At this point, the loss function also decreases gradually, while the loss factor tends to 0, which verifies the stability of the optimized model. According to the participants’ interaction experience and experimental results, the optimized LayerGesture technique of the federated learning model has an average correctness rate of 90.4% and the lowest average selection time, while the average selection time of LayerGesture in the interaction area at the edge of the screen is 2510 ms and the average correctness rate is 93.60%, which is better than the Shift technique. In addition, the subjective survey results indicated that more participants favored the optimized LayerGesture technique. In summary, this paper’s joint learning algorithm contributes to the recognition effectiveness and efficiency of intelligent interactive systems.

LSBlocFL: A secure federated learning model combining blockchain and lightweight cryptographic solutions

In the area of privacy protection, federated learning has received a lot of attention as an emerging distributed network training model that can effectively protect the privacy of users’ local data while completing the training task.However, existing federated learning (FL) models still face many security threats: (1) attackers can steal private data through gradients; (2) imposition of security measures reduces model accuracy; and (3) node crashes lead to failure of model training.To address these problems, this paper proposes a lightweight and secure blockchain federated learning(LSBlocFL) model with the following main ideas: (1) optimize the gradient encryption computation based on differential privacy (DP) and fully homomorphic encryption (FHE) scheme to ensure model accuracy while protecting privacy security; (2) build a decentralized FL training model by combining blockchain network to improve the security of model training environment; and (3) design user failure response mechanism. The model can guarantee accuracy under privacy protection, optimize encryption computation overhead, and enhance the decentralized secure network environment. Finally, experimental validation results on the CIFAR-10 dataset show that LSBlocFL has practically good performance.

FL-CTIF: A federated learning based CTI framework based on information fusion for secure IIoT

Industrial Internet of Things (IIoT) are evolving and transitioning into virtual entities supported by digital twin technology to optimize existing processes further and improve their efficiency. The virtual representation of the several IIoT departments, such as manufacturing process, packaging, warehousing, and logistics enables predictive maintenance for optimizing local material resources for manufacturing and packaging, improved warehouse space allocation, and delivery schedule optimization. The high volume of data generated from IoT devices are exposed to cyber-attacks using modern attack vectors and thus threaten both physical IIoT environment and its digital twins. Existing intrusion detection systems focus on identifying anomalous traffic using obsolete knowledge of cyber-attack patterns for several attacks, such as ARP poisoning man-in-the-middle attacks, SSL-based attacks using encrypted traffic, and DNS flood-based DDoS traffic. A lack of focus on security using updated and comprehensive Cyber Threat Intelligence (CTI) threatens the security of the IIoT environment. In this paper, we present a Federated Learning based CTI framework based on Information Fusion (FL-CTIF) for securing IIoT environments. We design a comprehensive cyberattack dataset with updated feature selection using Information Fusion to improve the accuracy in identifying cyber-attacks. A federated learning-based ANN model is designed to reduce the model training rounds based on satisfaction level and measure the absence of improvement in each attack vector's average accuracy. The model is evaluated based on model aggregation performance and demonstrates an improved F1 score based on reduced training rounds and reduced CPU consumption. The federated learning model improves accuracy and reduces the false positive rate using the newly merged dataset compared to existing research.

Accuracy–Security Tradeoff With Balanced Aggregation and Artificial Noise for Wireless Federated Learning

In federated learning (FL), a number of devices train their local models and upload the corresponding parameters or gradients to the base station (BS) for global model updates. However, the eavesdropper can recover data from parameters or gradients, resulting in data leakage. To defend against eavesdropping attacks, in this paper, we propose an algorithm that divides the transmit power proportionally between the transmitted signal and artificial noise (AN) to counteract the eavesdropper for wireless FL. In this algorithm, due to the limited communication resources, the ratio of signal power to total power and the aggregation frequency need to be carefully chosen, to guarantee the model accuracy and security at the same time. In order to achieve this goal, we maximize the secrecy rate with the system/user power and model performance constraints. To make this problem tractable, we derive two bounds of the secrecy rate and loss function, which allows us to obtain closed-form expressions for the power of AN and the aggregation frequency. Furthermore, in order to make our analysis more realistic, we consider the FL model with channel fading and additive white Gaussian noise (AWGN) over uplink and downlink respectively. Specifically, we discuss the convergence of FL over noisy multiple access channels (MACs). Simulation results confirm the convergence and the effectiveness of the proposed algorithm.

Dynamically Synthetic Images for Federated Learning of medical images

BackgroundTo develop deep learning models for medical diagnosis, it is important to collect more medical data from several medical institutions. Due to the regulations for privacy concerns, it is infeasible to collect data from various medical institutions to one institution for centralized learning. Federated Learning (FL) provides a feasible approach to jointly train the deep learning model with data stored in various medical institutions instead of collected together. However, the resulting FL models could be biased towards institutions with larger training datasets. MethodologyIn this study, we propose the applicable method of Dynamically Synthetic Images for Federated Learning (DSIFL) that aims to integrate the information of local institutions with heterogeneous types of data. The main technique of DSIFL is to develop a synthetic method that can dynamically adjust the number of synthetic images similar to local data that are misclassified by the current model. The resulting global model can handle the diversity in heterogeneous types of data collected in local medical institutions by including the training of synthetic images similar to misclassified cases in local collections. ResultsIn model performance evaluation metrics, we focus on the accuracy of each client's dataset. Finally, the accuracy of the model of DSIFL in the experiments can achieve the higher accuracy of the FL approach. ConclusionIn this study, we propose the framework of DSIFL that achieves improvements over the conventional FL approach. We conduct empirical studies with two kinds of medical images. We compare the performance by variants of FL vs. DSIFL approaches. The performance by individual training is used as the baseline, whereas the performance by centralized learning is used as the target for the comparison studies. The empirical findings suggest that the DSIFL has improved performance over the FL via the technique of dynamically synthetic images in training.

Block chain-Based Federated Learning: Incentivizing Data Sharing and Penalizing Dishonest Behavior

With the increasing importance of data sharing for collaboration and innovation, it is becoming more important to ensure that data is managed and shared in a secure and trustworthy manner. Data governance is a common approach to managing data, but it faces many challenges such as data silos, data consistency, privacy, security, and access control. To address these challenges, this paper proposes a comprehensive framework that integrates data trust in federated learning with Inter Planetary File System, block chain, and smart contracts to facilitate secure and mutually beneficial data sharing while providing incentives, access control mechanisms, and penalizing any dishonest behavior. The experimental results demonstrate that the proposed model is effective in improving the accuracy of federated learning models while ensuring the security and fairness of the data-sharing process. The research paper also presents a decentralized federated learning platform that successfully trained a CNN model on the MNIST dataset using block chain technology. The platform enables multiple workers to train the model simultaneously while maintaining data privacy and security. The decentralized architecture and use of block chain technology allow for efficient communication and coordination between workers. This platform has the potential to facilitate decentralized machine learning and support privacy preserving collaboration in various domains.

A Federated Learning Model Based on Hardware Acceleration for the Early Detection of Alzheimer's Disease.

Alzheimer's disease (AD) is a progressive illness with a slow start that lasts many years; the disease's consequences are devastating to the patient and the patient's family. If detected early, the disease's impact and prognosis can be altered significantly. Blood biosamples are often employed in simple medical testing since they are cost-effective and easy to collect and analyze. This research provides a diagnostic model for Alzheimer's disease based on federated learning (FL) and hardware acceleration using blood biosamples. We used blood biosample datasets provided by the ADNI website to compare and evaluate the performance of our models. FL has been used to train a shared model without sharing local devices' raw data with a central server to preserve privacy. We developed a hardware acceleration approach for building our FL model so that we could speed up the training and testing procedures. The VHDL hardware description language and an Altera 10 GX FPGA are utilized to construct the hardware-accelerator approach. The results of the simulations reveal that the proposed methods achieve accuracy and sensitivity for early detection of 89% and 87%, respectively, while simultaneously requiring less time to train than other algorithms considered to be state-of-the-art. The proposed algorithms have a power consumption ranging from 35 to 39 mW, which qualifies them for use in limited devices. Furthermore, the result shows that the proposed method has a lower inference latency (61 ms) than the existing methods with fewer resources.

Medical Imaging Applications of Federated Learning.

Since its introduction in 2016, researchers have applied the idea of Federated Learning (FL) to several domains ranging from edge computing to banking. The technique's inherent security benefits, privacy-preserving capabilities, ease of scalability, and ability to transcend data biases have motivated researchers to use this tool on healthcare datasets. While several reviews exist detailing FL and its applications, this review focuses solely on the different applications of FL to medical imaging datasets, grouping applications by diseases, modality, and/or part of the body. This Systematic Literature review was conducted by querying and consolidating results from ArXiv, IEEE Xplorer, and PubMed. Furthermore, we provide a detailed description of FL architecture, models, descriptions of the performance achieved by FL models, and how results compare with traditional Machine Learning (ML) models. Additionally, we discuss the security benefits, highlighting two primary forms of privacy-preserving techniques, including homomorphic encryption and differential privacy. Finally, we provide some background information and context regarding where the contributions lie. The background information is organized into the following categories: architecture/setup type, data-related topics, security, and learning types. While progress has been made within the field of FL and medical imaging, much room for improvement and understanding remains, with an emphasis on security and data issues remaining the primary concerns for researchers. Therefore, improvements are constantly pushing the field forward. Finally, we highlighted the challenges in deploying FL in medical imaging applications and provided recommendations for future directions.

RETRACTED ARTICLE: Enhancing throughput using channel access priorities in frequency hopping network using federated learning

The data are sent by the nodes taking part in frequency hopping communications (FHC) utilising carrier frequencies and time slots that are pseudo-randomly assigned. Because of this, a high degree of protection against eavesdropping and anti-interference capabilities is provided. When using FHC in an environment, sharing time and frequency resources, avoiding collisions, and differentiating services are all made more complex as a result of this. A protocol for FHC that is based on dispersed wireless networks is presented by the authors of this research. It is a mechanism for multiple access control, which is prioritised and distributed. The ratio of empty channels metric can be found in the previous sentence. It is possible to provide priority in channel access by assigning different preset ratios of empty channel thresholds to the various traffic classes. Frames from frequency spread segments that have a partial collision are included as well. An analytical model is simulated for the analysis in terms of collision probability, transmission probability, and frame service time in order to carry out a theoretical examination of the performance of FHC. The objective of this inquiry is to determine how well FHC works. The analytical model has been proven correct by the exhaustive simulations as well as the theoretical findings. Cloud platforms are often used in the instruction of the most cutting-edge machine learning techniques of today, such as deep neural networks. This is done in order to take advantage of the cloud's capacity to scale elastically. In order to satisfy the criteria of these sorts of applications, federated learning, has been proposed as a distributed machine learning solution. This is done in order to fulfil the requirements of these kinds of applications. In federated learning (FL), even though everyone who uses the system works together to train a model, nobody ever shares their data with anybody else. Each user trains a local model with their own data, and then communicates the updated models with a FL server so that the data can be aggregated and a global model can be constructed. This process ensures that each user's model is unique. This process is repeated until a global model has been developed. This kind of training not only reduces the amount of network overhead that is necessary to transfer data to a centralised server, but it also safeguards the personal information of the users. Within the framework of this work, we looked at the feasibility of using the FL technique of learning on the many devices that are part of the dispersed network. On a centralised server, we conduct an analysis of the performance of the FL model by comparing its accuracy and the amount of time it takes to train using a range of various parameter value combinations. Additionally, the accuracy of these federated models may be made to reach a level that is comparable to that of the accuracy of central models.

Federated learning based futuristic biomedical big-data analysis and standardization.

Medical data processing and analytics exert significant influence in furnishing dependable decision support for prospective biomedical applications. Given the sensitive nature of medical data, specialized techniques and frameworks tailored for application-centric processing are imperative. This article presents a conceptualization for the analysis and uniformitarian of datasets through the implementation of Federated Learning (FL). The realm of medical big data stems from diverse origins, necessitating the delineation of data provenance and attribute paradigms to facilitate feature extraction and dependency assessment. The architecture governing the data collection framework is intricately linked to remote data transmission, thereby engendering efficient customization oversight. The operational methodology unfolds across four strata: the data origin layer, data acquisition layer, data classification layer, and data optimization layer. Central to this endeavor are multi-objective optimal datasets (MooM), characterized by attribute-driven feature cartography and cluster categorization through the conduit of federated learning models. The orchestration of feature synchronization and parameter extraction transpires across multiple tiers of neural networking, culminating in the provisioning of a steadfast remedy through dataset standardization and labeling. The empirical findings reflect the efficacy of the proposed technique, boasting an impressive 97.34% accuracy rate in the disentanglement and clustering of telemedicine data, facilitated by the operational servers within the ambit of the federated model.

RETRACTED ARTICLE: Blockchain managed federated learning for a secure IoT framework

In this work, we present a blockchain-based federated learning (FL) framework that aims achieving high system efficiency while simultaneously addressing issues relating to data sparsity and the disclosure of private information. It is more efficient to build a number of smaller clusters rather than one big cluster for multiple networks. Blockchain-based FL is carried out in each cluster, with the model changes being compiled at the end of the process. Following that, the accumulated updates are swapped across the clusters, which, in practise, improves the updates that are accessible for each cluster. When compared to the extensive interactions that take place in blockchain-based FL, cluster-based FL only sends a limited number of aggregated updates across a substantial distance. This is in contrast to the extensive interactions that take place in blockchain-based FL. In order to conduct an analysis of our system, we have implemented the prototypes of both cluster and blockchain-based FL models. The findings of the experiments show that cluster-based FL model raise the accuracy goes upto 72.6%, and goes down to 11%. The loss goes upto 3.6 and goes down to 0.8. In addition, cluster-based FL model has the potential to hasten the convergence of the model, provided that the same quantity of data is input into it. The reason for this is due to the fact that during a training cycle, cluster-based FL model combines the computational resources of many different clusters.

Federated Multi-organ Segmentation with Inconsistent Labels.

Federated learning is an emerging paradigm allowing large-scale decentralized learning without sharing data across different data owners, which helps address the concern of data privacy in medical image analysis. However, the requirement for label consistency across clients by the existing methods largely narrows its application scope. In practice, each clinical site may only annotate certain organs of interest with partial or no overlap with other sites. Incorporating such partially labeled data into a unified federation is an unexplored problem with clinical significance and urgency. This work tackles the challenge by using a novel federated multi-encoding U-Net (Fed-MENU) method for multi-organ segmentation. In our method, a multi-encoding U-Net (MENU-Net) is proposed to extract organ-specific features through different encoding sub-networks. Each sub-network can be seen as an expert of a specific organ and trained for that client. Moreover, to encourage the organ-specific features extracted by different sub-networks to be informative and distinctive, we regularize the training of the MENU-Net by designing an auxiliary generic decoder (AGD). Extensive experiments on six public abdominal CT datasets show that our Fed-MENU method can effectively obtain a federated learning model using the partially labeled datasets with superior performance to other models trained by either localized or centralized learning methods. Source code is publicly available at https://github.com/DIAL-RPI/Fed-MENU.

Toward Federated Learning Models Resistant to Adversarial Attacks

Toward Federated Learning Models Resistant to Adversarial Attacks

A Fog-Based Privacy-Preserving Federated Learning System for Smart Healthcare Applications

During the COVID-19 pandemic, the urgency of effective testing strategies had never been more apparent. The fusion of Artificial Intelligence (AI) and Machine Learning (ML) models, particularly within medical imaging (e.g., chest X-rays), holds promise in smart healthcare systems. Deep Learning (DL), a subset of AI, has exhibited prowess in enhancing classification accuracy, a crucial aspect in expediting COVID-19 diagnosis. However, the journey to harness DL’s potential is rife with challenges: notably, the intricate landscape of medical data privacy. Striking a balance between utilizing patient data for insights while upholding privacy is formidable. Federated Learning (FL) emerges as a solution by enabling collaborative model training across decentralized data sources, thus bypassing data centralization and preserving data privacy. This study presents a tailored, collaborative FL architecture for COVID-19 screening via chest X-ray images. Designed to facilitate cooperation among medical institutions, the framework ensures patient data remain localized, eliminating the need for direct data sharing. Addressing imbalanced and non-identically distributed data, the architecture is a robust solution. Implementation entails localized and fog-computing-based FL models. Localized models utilize Convolutional Neural Networks (CNNs) on institution-specific datasets, while the FL model, refined iteratively, takes precedence in the final classification. Intriguingly, the global FL model, fortified by fog computing, emerges as the frontrunner in classification after weight refinement, surpassing local models. Validation within the COLAB platform gauges the model’s performance through metrics such as accuracy, precision, recall, and F1-score. Remarkably, the proposed model excels across these metrics, solidifying its efficacy. This research navigates the confluence of AI, FL, and medical imaging, unveiling insights that could reshape healthcare delivery. The study enriches scientific discourse by addressing data privacy in collaborative learning and carries potential implications for enhanced patient care.

Federated Transfer Learning for Rice-Leaf Disease Classification across Multiclient Cross-Silo Datasets

Paddy leaf diseases encompass a range of ailments affecting rice plants’ leaves, arising from factors like bacteria, fungi, viruses, and environmental stress. Precision agriculture leverages technologies for enhanced crop production, with disease detection being a vital element. Prompt identification of diseases in paddy leaves is critical for curtailing their propagation and reducing crop damage. However, manually diagnosing paddy diseases in regions with vast agricultural areas and limited experts proves immensely difficult. The utilization of machine learning (ML) and deep learning (DL) for diagnosing diseases in agricultural crops appears to be effective and well-suited for widespread application. These ML/DL methods cannot ensure data privacy, as they involve sharing training data with a central server, overlooking competitive and regulatory considerations. As a solution, federated learning (FL) aims to facilitate decentralized training to tackle the identified limitations of centralized training. This paper utilizes the FL approach for the classification of rice-leaf diseases. The manuscript presents an effective approach for rice-leaf disease classification with a federated architecture, ensuring data privacy. We have compiled an unbalanced dataset of rice-leaf disease images, categorized into four diseases with their respective image counts: bacterial blight (1584), brown spot (1440), blast (1600), and tungro (1308). The proposed method, called federated transfer learning (F-TL), maintains privacy for all connected devices using a decentralized client-server setup. Both IID (independent and identically distributed) and non-IID datasets were utilized for testing the F-TL framework after preprocessing. Initially, we conducted an effectiveness analysis of CNN and eight transfer learning models for rice-leaf disease classification. Among them, MobileNetV2 and EfficientNetB3 outperformed the other transfer-learned models. Subsequently, we trained these models using both IID and non-IID datasets in a federated learning environment. The framework’s performance was assessed through diverse scenarios, comparing it with traditional and federated learning models. The evaluation considered metrics like validation accuracy, loss as well as resource utilization such as CPU and RAM. EfficientNetB3 excelled in training, achieving 99% accuracy with 0.1 loss for both IID and non-IID datasets. MobilenetV2 showed slightly lower training accuracy at 98% (IID) and 90% (non-IID) with losses of 0.4 and 0.6, respectively. In evaluation, EfficientNetB3 maintained 99% accuracy with 0.1 loss for both datasets, while MobilenetV2 achieved 90% (IID) and 97% (non-IID) accuracy with losses of 0.6 and 0.2, respectively. Results indicated the F-TL framework’s superiority over traditional distributed deep-learning classifiers, demonstrating its effectiveness in both single and multiclient instances. Notably, the framework’s strengths lie in its cost-effectiveness and data-privacy assurance for resource-constrained edge devices, positioning it as a valuable alternative for rice-leaf disease classification compared to existing tools.

Unmanned Aerial Vehicle-Assisted Federated Learning Method Based on a Trusted Execution Environment

In the face of increasing concerns around privacy and security in the use of unmanned aerial vehicles (UAVs) for mobile edge computing (MEC), this study proposes a novel approach to secure UAV-assisted federated learning. This research integrates a trusted execution environment (TEE) into UAV-assisted federated learning and proposes a robust aggregation algorithm based on cosine distance, denoted as CosAvg. This study further designs and evaluates a TEE-based federated learning model, comparing its resource overhead with other secure aggregation frameworks, like homomorphic encryption (HE) and differential privacy (DP). Experimental results indicate a significant reduction in resource overhead for TEE against DP and HE. Moreover, the proposed CosAvg algorithm demonstrated superior robustness against adversarial scenarios, maintaining high accuracy in the presence of malicious clients. The integration of TEE and the CosAvg algorithm provides a secure and robust solution for UAV-assisted federated learning, effectively defending both gradient inversion attacks and byzantine attacks.

FedBrain: A robust multi-site brain network analysis framework based on federated learning for brain disease diagnosis

In recent years, deep learning models have shown their advantages in neuroimage analysis, such as brain disease diagnosis. Unfortunately, it is usually difficult to acquire numerous brain networks at a single centralized site to effectively train a high-quality deep learning model. To address this issue, federated learning (FL) has gained popularity in brain disease diagnosis, which allows deep learning models to be trained without centralizing data. However, most FL-based works might still face two following challenges. Firstly, the high-dimensional features of brain networks are often far larger than sample size, which might lead to poor performance due to the curse of dimensionality. Secondly, differences in data distributions across different sites can impact the communication efficiency and performance of FL models. To overcome these challenges, we design a novel FL framework for diagnosing brain disorders, named FedBrain. Firstly, FedBrain proposes data augmentation based on L1 regularization to select significant features shared by all clients. The domain alignment loss based on the maximum mean discrepancy criterion is introduced to minimize differences in the marginal and conditional distributions between local clients. Furthermore, FedBrain proposes a personalized predictor based on mixture of experts to adapt to different clients, using a global and private predictor as two experts. Eventually, FedBrain integrates the above modules with differential privacy and homomorphic encryption into a unified FL framework. Experimental results on the Autism Brain Imaging Data Exchange (ABIDE) dataset demonstrate its effectiveness and robustness, which shows that FedBrain can reduce the communication burden of FL and achieve the highest average accuracy of 79% against other counterparts.

Adaptive Quantization Mechanism for Federated Learning Models Based on DAG Blockchain

With the development of the power internet of things, the traditional centralized computing pattern has been difficult to apply to many power business scenarios, including power load forecasting, substation defect detection, and demand-side response. How to perform efficient and reliable machine learning tasks while ensuring that user data privacy is not violated has attracted the attention of the industry. Blockchain-based federated learning (FL), proposed as a new decentralized and distributed learning framework for building privacy-enhanced IoT systems, is receiving more and more attention from scholars. The framework provides some advantages, including decentralization, scalability, and data privacy, but at the same time its consensus mechanism consumes a significant amount of computational resources. Moreover, the number of model parameters has increased dramatically, leading to an increasing amount of transmitted data and a vast communication overhead. To reduce the communication overhead, we propose an FL framework in the directed acyclic graph (DAG)-based blockchain system, which achieves efficient and trusted sharing of FL networks. We design an adaptive model compression method based on k-means to compress the FL model and reduce the communication overhead of each round in FL training. Meanwhile, the original accuracy-based tips selection algorithm is optimized, and a tips selection algorithm considering multi-factor evaluation is proposed. Simulation experimental results show that the method proposed in this paper reduces the total bytes of communication of the blockchain-based federated learning system while balancing the accuracy of the FL model compared to previous work.

GoMORE: Global Model Reuse for Resource-Constrained Wireless Federated Learning

Due to the dynamics of wireless channels and limited wireless resources (i.e., spectrum), deploying federated learning (FL) over wireless networks is challenged by frequent FL parameter transmission errors and incomplete FL model aggregation from devices. In order to overcome these challenges, we propose a Global MOdel REuse strategy (GoMORE) that reuses global FL models received at previous FL training iterations to replace erroneous local models caused by imperfect wireless transmissions. We analytically prove that the proposed GoMORE is strictly superior over the existing strategy, especially at low signal-to-noise ratios (SNRs). Based on the derived expression of weight divergence, we optimize the number of devices that participate in the model aggregation to maximize the FL performance with limited communication resources. Numerical results verify that the proposed GoMORE successfully approaches the performance upper bound by an ideal transmission. It also mitigates the negative impacts of non-independent and non-identically distributed (non-IID) data while achieving over 5 dB reduction in energy consumption.