Cooperative Swarm Learning for Distributed Cyclic Edge Intelligent Computing

We study federated edge learning, where a global model is trained collaboratively using privacy-sensitive data at the edge of a wireless network. A parameter server (PS) keeps track of the global model and shares it with the wireless edge devices for training using their private local data. The devices then transmit their local model updates, which are used to update the global model, to the PS. The algorithm, which involves transmission over PS-to-device and device-to-PS links, continues until the convergence of the global model or lack of any participating devices. In this study, we consider device selection based on downlink channels over which the PS shares the global model with the devices. Performing digital downlink transmission, we design a partial device participation framework where a subset of the devices is selected for training at each iteration. Therefore, the participating devices can have a better estimate of the global model compared to the full device participation case which is due to the shared nature of the broadcast channel with the price of updating the global model with respect to a smaller set of data. At each iteration, the PS broadcasts different quantized global model updates to different participating devices based on the last global model estimates available at the devices. We investigate the best number of participating devices through experimental results for image classification using the MNIST dataset with biased distribution.

Federated learning (FL) has been vigorously promoted in wireless edge networks as it fosters collaborative training of machine learning (ML) models while preserving individual user privacy and data security. In conventional FL, user equipment (UE) and an aggregator can collaboratively train shared global ML models by transmitting interactive ML models. In wireless edge networks, heterogeneity of multi-dimensional resources (e.g., computing and communication resources) used to train and transmit FL models may introduce stragglers, characterized by a slow update and/or transmission of local models. The stragglers can significantly degrade learning performance of FL, as the slowest participating UE can dramatically slow down the entire convergence. In this paper, to alleviate the negative impact of stragglers, we propose a dynamic straggler-aware clustering based FL (FeDSC) mechanism via adaptive UE clustering. Specifically, we first group participating UEs into multiple clusters based on their available computing and wireless resources. Then, we propose an adaptive clustering scheme to synchronously update the cluster aggregation model. Meanwhile, an edge server performs global aggregation of different cluster models in an asynchronous manner. Finally, we theoretically demonstrate the convergence of our proposed mechanism via numerical results. Numerical results show that our proposed mechanism can effectively reduce training time and wireless bandwidth consumption, while improving training efficiency and guaranteeing learning accuracy.

<span lang="EN-US">With the proliferation of internet of things (IoT) devices, ensuring the security of these interconnected systems has become a critical concern. Cyberattacks targeting IoT devices pose significant threats to individuals and organizations due to the generation of vast amounts of data across many connected devices, which traditional centralized methods cannot solve. Federated learning (FL) could be a promising solution to mitigate privacy concerns associated with centralized approaches and address cybersecurity concerns. This paper uses FL and deep learning (DL) approaches to cybersecurity in IoT applications. The goal of cyber security is achieved by forming a federation of acquired and shared models at the head of the various participants. We use inception time and multi-head attention (CNN) algorithm based on FL to detect cyber-attacks and avoid data privacy leaks under two distribution modes, namely IID and Non-IID. In contrast, the FedAvg and FedMA algorithms aggregate local model updates. A global model is produced after several communication rounds between the IoT devices and the model parameter server. Cyber threats are simulated using edge-IIoT datasets. Experiment results show that the federated inception model's best global accuracy was 93, 91%, and 93, 49% using multi-head attention.</span>

Artificial intelligence (AI) has, in the recent past, experienced a rebirth with the growth of generative AI systems such as ChatGPT and Bard. These systems are trained with billions of parameters and have enabled widespread accessibility and understanding of AI among different user groups. Widespread adoption of AI has led to the need for understanding how machine learning (ML) models operate to build trust in them. An understanding of how these models generate their results remains a huge challenge that explainable AI seeks to solve. Federated learning (FL) grew out of the need to have privacy-preserving AI by having ML models that are decentralized but still share model parameters with a global model. This study sought to examine the extent of development of the explainable AI field within the FL environment in relation to the main contributions made, the types of FL, the sectors it is applied to, the models used, the methods applied by each study, and the databases from which sources are obtained. A systematic search in 8 electronic databases, namely, Web of Science Core Collection, Scopus, PubMed, ACM Digital Library, IEEE Xplore, Mendeley, BASE, and Google Scholar, was undertaken. A review of 26 studies revealed that research on explainable FL is steadily growing despite being concentrated in Europe and Asia. The key determinants of FL use were data privacy and limited training data. Horizontal FL remains the preferred approach for federated ML, whereas post hoc explainability techniques were preferred. There is potential for development of novel approaches and improvement of existing approaches in the explainable FL field, especially for critical areas. OSF Registries 10.17605/OSF.IO/Y85WA; https://osf.io/y85wa.

Federated Learning (FL) is a paradigm in distributed machine learning, which has gained significant attention in the recent years especially in the domain of Internet of Things. Federated Learning saves communication bandwidth when compared to centralized machine learning process and is also considered to be privacy preserving as the raw data at the clients need not be transmitted to the server for the FL learning. Recent studies on FL have exposed privacy vulnerabilities particularly in the form of Gradient Leakage Attacks (GLA) in which the adversaries can generate training data of the client from shared gradients or model updates from clients. The available solutions in the literature for GLA based on perturbing the gradients from clients leads to a drop in the performance of the FL system while attempting to preserve privacy. We propose HAFedL, an improved novel hessian aware adaptive privacy preserving FL scheme in which the performance of the model is not significantly affected due to the aspects introduced in the FL architecture to improve the privacy of the model against the GLA. The HAFedL is also robust to the data heterogeneity and device heterogeneity (particularly straggler effect) which may be present in the clients participating in the FL. The performance of HAFedL is tested for two applications- IoT device identification and digit classification. The proposed HAFedL scheme can be utilized in privacy sensitive domains such as smart city applications, Industrial Internet of Things, Internet of Robotic Things, Internet of Medical Things, etc.

Mobile and Web-of-Things (WoT) devices at the network edge account for more than half of the world's web traffic, making a great data source for various machine learning (ML) applications, particularly federated learning (FL) which offers a promising solution to privacy-preserving ML feeding on these data. FL allows edge mobile and WoT devices to train a shared global ML model under the orchestration of a central parameter server. In the real world, due to resource heterogeneity, these edge devices often train different versions of models (e.g., VGG-16 and VGG-19) or different ML models (e.g., VGG and ResNet) for the same ML task (e.g., computer vision and speech recognition). Existing FL schemes have assumed that participating edge devices share a common model architecture, and thus cannot facilitate FL across edge devices with heterogeneous ML model architectures. We explored this architecture heterogeneity challenge and found that FL can and should accommodate these edge devices to improve model accuracy and accelerate model training. This paper presents our findings and FlexiFed, a novel scheme for FL across edge devices with heterogeneous model architectures, and three model aggregation strategies for accommodating architecture heterogeneity under FlexiFed. Experiments with four widely-used ML models on four public datasets demonstrate 1) the usefulness of FlexiFed; and 2) that compared with the state-of-the-art FL scheme, FlexiFed improves model accuracy by 2.6%-9.7% and accelerates model convergence by 1.24 × -4.04 ×.

In this paper, the optimization of network performance to support the deployment of federated learning (FL) is investigated. In particular, in the considered model, each user owns a machine learning (ML) model by training through its own dataset, and then transmits its ML parameters to a base station (BS) which aggregates the ML parameters to obtain a global ML model and transmits it to each user. Due to limited radio frequency (RF) resources, the number of users that participate in FL is restricted. Meanwhile, each user uploading and downloading the FL parameters may increase communication costs thus reducing the number of participating users. To this end, we propose to introduce visible light communication (VLC) as a supplement to RF and use compression methods to reduce the resources needed to transmit FL parameters over wireless links so as to further improve the communication efficiency and simultaneously optimize wireless network through user selection and resource allocation. This user selection and bandwidth allocation problem is formulated as an optimization problem whose goal is to minimize the training loss of FL. We first use a model compression method to reduce the size of FL model parameters that are transmitted over wireless links. Then, the optimization problem is separated into two subproblems. The first subproblem is a user selection problem with a given bandwidth allocation, which is solved by a traversal algorithm. The second subproblem is a bandwidth allocation problem with a given user selection, which is solved by a numerical method. The ultimate user selection and bandwidth allocation are obtained by iteratively compressing the model and solving these two subproblems. Simulation results show that the proposed FL algorithm can improve the accuracy of object recognition by up to 16.7% and improve the number of selected users by up to 68.7%, compared to a conventional FL algorithm using only RF.

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.

The Internet of Things (IoT) realized exponential growth of smart devices with decent capabilities, promising an era of Edge Intelligence. This paradigm creates a timely need to shift many computations closer to the data source at the network's edge. Data privacy is paramount, as security breaches can severely impact such an environment with its vast attack surface. The advent of Federated learning (FL), a privacy-by-design with decentralized machine learning (ML), enables participants to collaboratively train a model without sharing their sensitive data. Nevertheless, privacy implications are a glaring concern and perrier for widening the utilization of FL approaches and their mass adoption over IoT applications. This paper introduces the notion of FL over the Internet of Disconnected Things (FLIoDT), a functionality separation of concerns following the air-gapped networks. FLIoDT provides a practical methodology to mitigate Data threats/attacks in the FL domain. FLIoDT proves a practical architectural approach to mitigate several attacks in an Edge environment. Data dredging and adversarial attacks, like data poisoning, to name some. This study investigates human activity recognition of health monitoring patient data over edge computing to validate FLIoDT.

The recent surge in edge computing and wireless connectivity has accelerated the adoption of Federated Learning (FL), a paradigm that enables privacy-preserving distributed intelligence across resource-constrained devices. However, implementing FL in practical wireless edge networks introduces significant challenges, particularly excessive energy consumption and communication overhead. This survey provides a system-level exploration of energy-efficient FL strategies, examining algorithmic advances and deployment challenges. Core techniques—such as model compression, update sparsification, and adaptive client scheduling—are analyzed with respect to their trade-offs in scalability, convergence, and long-term energy sustainability, especially under non-IID data distributions and heterogeneous device conditions. Practical insights are drawn from case studies in the Internet of Things (IoT), 5G/6G wireless ecosystems, and ultra-low-power device deployments, highlighting both limitations and optimization opportunities for real-world implementations. In addition, the survey explores emerging enablers, including blockchain-based trust frameworks, neuromorphic processors, and reinforcement learning-driven orchestration, which hold potential for achieving robust, sustainable FL in dynamic edge environments. By integrating perspectives from communication theory, distributed systems, and sustainable computing, this work delivers an interdisciplinary roadmap for the realistic deployment of energy-efficient FL in next-generation wireless systems, aiming to guide future research toward scalable, fair, and sustainable federated intelligence at the wireless edges.

As a novel distributed machine learning approach, federated learning (FL) is proposed to train a global model while preserving data privacy. However, some studies manifest that adversaries can still recover private information from the gradients. Differential privacy (DP) is a rigorous mathematical tool to protect records in a database against leakage. It has been widely applied in FL by perturbing the gradients. Nevertheless, while using DP in FL, the convergence performance of the global model is inevitably degraded. In this paper, we implement a DP-based FL scheme, which achieves local DP (LDP) by adding well-designed Gaussian noise on the gradients before clients upload them to the server. After that, we propose two strategies to improve the convergence performance of the DP-based FL. Both methods are realized by modifying the local objective function to limit the effect of LDP noise on convergence without degrading the privacy protection level. We then provide the detailed framework which adopts the LDP scheme and two strategies. The framework on different machine learning models is tested by simulation results, which show that our framework can improve the convergence performance up to 40% faster under different noise compared with other DP-based FL. Finally, we show the theoretical convergence guarantee of our proposed framework by first presenting the expected decrease in the global loss function for one round of training and then providing the upper convergence bound after multiple communication rounds.

Cyber-physical systems (CPS) have evolved over the years and are now integrated into intelligent manufactory. The Internet of Things (IoT) has played a significant role in the advancement of such systems. CPS have become more intelligent and self-automated with the aid of advances in Artificial Intelligence (AI). Automating the process of CPS management requires that AI and secure transaction processing be integrated within all stakeholders, including the cloud, fog, edge, network, storage, and industrial devices. This integration necessitates the distribution and decentralization of the self-configuring, self-managing, self-healing, and self-governing process in CPS. This paper presents a blockchain-based hierarchical federated learning (HFL) solution that maintains quick, secure, and accurate decision-making for industrial machines. A two-stage federated learning (FL) algorithm, where during the first stage, industrial devices are grouped into clusters and perform local ML training. Local models are shared with network edge devices and a set of global models are created using FL averaging. During the second stage, a main global model is created from the distributed first-stage global models using a FL aggregating algorithm. Blockchain is used to verify and validate the trained models on the edge. System evaluations are performed to compare the proposed HFL solution against traditional FL in terms of training accuracy and network overhead.

Federated learning (FL) has been used to several domains, such as smart cities, intelligent healthcare systems, and sectors reliant on the internet of things (IoT). This is in response to the growing concern about privacy and security in machine learning applications. Clients may work together to train a global model using FL, even when they don't have access to the same data as before. Nevertheless, adversarial attacks may exploit the weaknesses of existing FL methods. Because of its design, protecting against harmful model changes and identifying them are both made difficult. Not enough has been investigated in the most current research on protecting the model's privacy while detecting FL from harmful updates. This study presented a solution to the problem of poisoning assaults on healthcare systems: federated learning based on blockchain technology with SMPC model verification. We start by removing the compromised model after verifying it via an encrypted inference procedure using the FL participants' machine learning models. After each participant's local model is checked, it is safely forwarded to the blockchain node for aggregation. In order to test our proposed framework, we used a variety of medical datasets in a number of studies.

Emerging mobile edge techniques and applications such as Augmented Reality (AR)/Virtual Reality (VR), Internet of Things (IoT), and vehicle networking, result in an explosive growth of power and computing resource consumptions. In the meantime, the volume of data generated at the edge networks is also increasing rapidly. Under this circumstance, building energy-efficient and privacy-protected communications is imperative for 5G and beyond wireless communication systems. The recent emerging distributed learning methods such as federated learning (FL) perform well in improving resource efficiency while protecting user privacy with low communication overhead. Specifically, FL enables edge devices to learn a shared network model by aggregating local updates while keeping all the training processes on local devices. This paper investigates distributed power allocation for edge users in decentralized wireless networks with aim to maximize energy/spectrum efficiency while preventing privacy leakage based on a FL framework. Due to the dynamics and complexity of wireless networks, we adopt an on-line Actor-Critic (AC) architecture as the local training model, and FL performs cooperation for edge users by sharing the gradients and weightages generated in the Actor network. Moreover, in order to resolve the over-fitting problem caused by data leakages in Non-independent and identically distributed (Non-i.i.d) data environment, we propose a federated augmentation mechanism with Wasserstein Generative Adversarial Networks (WGANs) algorithm for data augmentation. Federated augmentation empowers each device to replenish the data buffer using a generative model of WGANs until accomplishing an i.i.d training dataset, which significantly reduces the communication overhead in distributed learning compared to direct data sample exchange method. Numerical results reveal that the proposed federated learning based cooperation and augmentation (FL-CA) algorithm possesses a good convergence property, high robustness and achieves better accuracy of power allocation strategy than other three benchmark algorithms.

Federated learning (FL) has arisen as an alternative to collecting large amounts of data in a central place to train a machine learning (ML) model. FL is privacy-friendly, allowing multiple parties to collaboratively train an ML model without exchanging or transmitting their training data. For this purpose, an aggregator iteratively coordinates the training process among parties, and parties simply share with the aggregator model updates, which contain information pertinent to the model such as neural network weights. Besides privacy, generalization has been another key driver for FL: parties who do not have enough data to train a good performing model by themselves can now engage in FL to obtain an ML model suitable for their tasks. Products and real applications in the industry and consumer space have demonstrated the power of this learning paradigm. Recently, foundation models have taken the AI community by storm, promising to solve the shortage of labeled data. A foundation model is a powerful model that can be recycled for a variety of use cases by applying techniques such as zero-shot learning and full or parameter-efficient fine tuning. The premise is that the amount of data required to fine tune a foundation model for a new task is much smaller than fully training a traditional model from scratch. The reason why this is the case is that a good foundation model has already learned relevant general representations, and thus, adapting it to a new task only requires a minimal number of additional samples. This raises the question: Is FL still alive in the era of foundation models? In this talk, I will address this question. I will present some use cases where FL is very much alive. In these use cases, finding a foundation model with a desired representation is difficult if not impossible. With this pragmatic point of view, I hope to shed some light into a real use case where disparate private data is available in isolation at different parties and where labels may be located at a single party that doesn’t have any other information, making it impossible for a single party to train a model on its own. Furthermore, in some vertically-partitioned scenarios, cleaning data is not an option due to privacy-related reasons and it is not clear how to apply foundation models. Finally, I will also go over a few other requirements that are often overlooked, such as unlearning of data and its implications for the lifecycle management of FL and systems based on foundation models.