Client Selection Research Articles

Data-Centric Client Selection for Federated Learning Over Distributed Edge Networks

This work presents an efficient data-centric client selection approach, named DICE, to enable federated learning (FL) over distributed edge networks. Prior research focused on assessing the computation and communication ability of the client devices for selection in FL. On-device data quality, in terms of data volume and heterogeneity, across these distributed devices is largely overlooked. The obvious outcome is the selection of an improper subset of clients with poor-quallity data, which inevitably results in an inefficient trained model. With an aim to address this problem, in this work, we design DICE which prioritizes the data quality of the client devices in the selection phase, in addition to their computation and communication abilities, to improve the accuracy of FL. Additionally, in DICE, we introduce the assistance of vicinal edge devices to account for the lack of computation or communication abilities in certain devices without violating the privacy-preserving guarantees of FL. Towards this aim, we propose a scheme to decide the optimal edge device, in terms of latency and workload, to be selected as the helper device. The experimental results show that DICE improves convergence speed for a given level of model accuracy. Further, the simulation results show that DICE reduces delay by at least 16%, energy consumption by at least 17%, and packet loss by at least 55% compared to the existing benchmarks while prioritizing the on-device data quality across clients.

Anti-Jamming Strategy for Federated Learning in Internet of Medical Things: A Game Approach.

Federated learning (FL) is a new dawn of artificial intelligence (AI), in which machine learning models are constructed in a distributed manner while communicating only model parameters between a centralized aggregator and client internet-of-medical-things (IoMT) nodes. The performance of such a learning technique can be seriously hampered by the activities of a malicious jammer robot. In this paper, we study client selection and channel allocation along with the power control problem of the uplink FL process in IoMT domain under the presence of a jammer from the perspective of long-term learning duration. We map the interaction between the FL network and the jammer in each learning iteration as a Stackelberg game, in which the jammer acts as the leader and the FL network serves as the follower. We consider the client and channel selection as well as the power control jointly as the strategy of this game. Upon formulating the game, we find the joint best response strategy for both types of players by leveraging the difference of convex (DC) programming approach and the dual decomposition technique. Beside the availability of the complete information to both the players, we also study the problem from the perspective that the FL network knows the partial information of the other player. Extensive simulations have been conducted to verify the effectiveness of the proposed algorithms in the jamming game.

A Truthful and Reliable Incentive Mechanism for Federated Learning Based on Reputation Mechanism and Reverse Auction

As a distributed machine learning paradigm, federated learning (FL) enables participating clients to share only model gradients instead of local data and achieves the secure sharing of private data. However, the lack of clients’ willingness to participate in FL and the malicious influence of unreliable clients both seriously degrade the performance of FL. The current research on the incentive mechanism of FL lacks the accurate assessment of clients’ truthfulness and reliability, and the incentive mechanism based on untruthful and unreliable clients is unreliable and inefficient. To solve this problem, we propose an incentive mechanism based on the reputation mechanism and reverse auction to achieve a more truthful, more reliable, and more efficient FL. First, we introduce the reputation mechanism to measure clients’ truthfulness and reliability through multiple reputation evaluations and design a reliable client selection scheme. Then the reverse auction is introduced to select the optimal clients that maximize the social surplus while satisfying individual rationality, incentive compatibility, and weak budget balance. Extensive experimental results demonstrate that this incentive mechanism can motivate more clients with high-quality data and high reputations to participate in FL with less cost, which increases the FL tasks’ economic benefit by 31% and improves the accuracy from 0.9356 to 0.9813, and then promote the efficient and stable development of the FL service trading market.

FEAT: A Federated Approach for Privacy-Preserving Network Traffic Classification in Heterogeneous Environments

Network traffic classification is the foundation for many network security and network management applications. Recently, to preserve the privacy of the data which are generated in the mobile ends, federated learning (FL)-based classification methods are being proposed. Unfortunately, the performance of FL-based methods can seriously degrade when the client data have skewness. This is particularly true for mobile network traffic classification where the environments in the mobile ends are highly heterogeneous. In this article, we first conduct a measurement study on traffic classification accuracy through FL using real-world network traffic trace and we observe serious accuracy degradation due to heterogeneous environments. We propose a novel federated analytics (FA) approach, FEAT, to improve the accuracy. Note that FL emphasizes on model training, yet our FA performs local analytic tasks that can estimate traffic data skewness and select appropriate clients for FL model training. Our analytics tasks are performed locally and in a federated manner; thus, we preserve privacy as well. Our approach has strong theoretical properties where we exploit Hoeffding inequality to infer traffic data skewness and we leverage the Thompson Sampling for client selection. We evaluate our approach through extensive experiments using real-world traffic data sets QUIC and ISCX. The extensive experiments demonstrate that FEAT can improve traffic classification accuracy in heterogeneous environments.

ModularFed: Leveraging modularity in federated learning frameworks

Numerous research recently proposed integrating Federated Learning (FL) to address the privacy concerns of using machine learning in privacy-sensitive firms. However, the standards of the available frameworks can no longer sustain the rapid advancement and hinder the integration of FL solutions, which can be prominent in advancing the field. In this paper, we propose ModularFed, a research-focused framework that addresses the complexity of FL implementations and the lack of adaptability and extendability in the available frameworks. We provide a comprehensive architecture that assists FL approaches through well-defined protocols covering three dominant FL paradigms: adaptable workflow, datasets distribution, and third-party application support. Within this architecture, protocols are blueprints that strictly define the framework’s components’ design, contribute to its flexibility, and strengthen its infrastructure. Further, our protocols aim to enable modularity in FL, supporting third-party plug-and-play architecture and dynamic simulators coupled with major built-in data distributors. Additionally, the framework support wrapping multiple approaches in a single environment to enable consistent replication of FL issues such as clients’ deficiency, data distribution, and network latency, which entails a fair comparison of techniques outlying FL technologies. In our evaluation, we examine the applicability of our framework addressing major FL domains, including statistical distribution and modular-based resource monitoring tools and client selection. Moreover, our comparison analysis indicates that our architecture has an inconsiderable impact on performance compared to other approaches.

Investigating the factors of selecting audit clients: Evidence from an emerging market

This study investigates the insights and criteria audit partners use to select prospective clients in an emerging market. We use questionnaires to solicit responses from a sample of auditors at the partner/manager level in Big and non-Big 4 audit firms with international affiliations in an emerging economy. Descriptive statistical tools including the chi-square test and multiple logistic regression analysis are used for the analysis. This study finds that auditor reputation enhancement and corporate governance effectiveness are significantly associated with the acceptance of listed companies and that the higher financial reporting quality of listed companies and the need to promote audit and assurance services are significant factors affecting such decisions. Audit firms tend to select parents or subsidiaries because of the expected effective audits and reduced misstatement and litigation risks and audit firm industry expertise is needed to mitigate expected client risks to significantly affect the selection of clients with prior-year audit qualifications. Fraud is significantly associated with the selection of clients with prior violations reported by government monitoring bodies. This study is among the few empirical studies in emerging economies that provide insights from practicing auditors on a set of comprehensive attributes that affect the selection of audit clients. The findings have implications for audit partners and firms, auditees, and the audit profession in selecting clients that fit the firm’s and profession’s vision of audit branding and reputation

Joint Client Selection and Receive Beamforming for Over-the-Air Federated Learning With Energy Harvesting

Federated learning (FL) is a well-regarded distributed machine learning technology that leverages local computing resources while protecting privacy. The over-the-air (OTA) computation has been adopted for FL to prevent excessive consumption of communication resources by employing the superposition nature of wireless waveform. Meanwhile, energy harvesting technology can relieve the energy constraint of clients and enable durable computation for FL. However, few of the existing works on OTA FL have considered jointly performing client selection and receive beamforming optimization with energy harvesting clients. The objective of this work is to address this issue to improve the learning performance of OTA FL. Specifically, we first derive the expression of the optimality gap regarding client selection and receive beamforming design. Then, to minimize the optimality gap, a mixed-integer nonlinear programming (MINLP) problem is formulated and decomposed into two sub-problems. Next, the semidefinite relaxation method and the channel-energy-data (CED)-based method are developed to optimize the receive beamforming sub-problem and client selection sub-problem iteratively. One alternative optimization method is proposed to deal with the decoupled sub-problems for obtaining the solutions to the original MINLP problem. Our simulation results demonstrate that the proposed solution is superior to the other comparison schemes in various parameter settings.

Data Distribution-Aware Online Client Selection Algorithm for Federated Learning in Heterogeneous Networks

Federated learning (FL) has received significant attention as a practical alternative to traditional cloud-centric machine learning (ML). The performance (e.g., accuracy and convergence time) of FL is hampered by the selection of clients having non-independent and identically distributed (non-IID) data. In addition, a long convergence time is inevitable if clients with poor computation or communication capabilities participate in the FL procedure (i.e., the straggler problem). To minimize convergence time while guaranteeing high learning accuracy, we first formulate an optimization problem on client selection. As a practical solution, we devise a data distribution-aware online client selection (DOCS) algorithm. In DOCS, the FL server finds several clusters having near IID data and then uses a multi-armed bandit (MAB) technique to select the cluster with the lowest convergence time. The evaluation results demonstrate that DOCS can reduce the convergence time by up to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$10\% \!\sim\! 41\%$</tex-math></inline-formula> and improve the learning accuracy by up to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$4\% \!\sim\! 13\%$</tex-math></inline-formula> compared to the traditional client selection schemes.

Federated Learning Resource Optimization and Client Selection for Total Energy Minimization Under Outage, Latency, and Bandwidth Constraints With Partial or No CSI

We consider the problem of minimizing the total energy consumption due to the computation and communication tasks of federated learning (FL) under bandwidth and latency constraints. To avoid channel state information (CSI) feedback to the transmitter, we adopt outage probability as an additional constraint in the energy minimization problem. First, we define a feasibility metric based on the system design parameters to exclude slow clients (stragglers). Then, we propose a novel client selection algorithm, after excluding stragglers, based on dividing the remaining clients into clusters, where clients within the same cluster collaborate in a communication round to train their local models. For each communication round, one client cluster is selected in a round-robin fashion. Furthermore, we formulate and solve a resource allocation problem to optimize the transmit power, clock frequency, allocated bandwidth, and communication latency of clients within each cluster to minimize the total energy subject to total bandwidth, latency, and outage constraints. Moreover, we extend our FL design framework to the case of no CSI at both the client and server ends using differential transmission to eliminate CSI estimation pilot overhead and complexity at comparable total energy consumption and learning accuracy to coherent transmission. We test our proposed algorithms over MNIST and Fashion-MNIST datasets in iid and non-iid settings. Our proposed client selection algorithm reduces the number of participating clients per communication round by 41% compared to the baseline while maintaining the same learning accuracy. Moreover, our results demonstrate that increasing the number of receive antennas at the server from one to four can reduce the number of communication rounds required to reach a predetermined testing accuracy level by up to 53% for the Fashion-MNIST dataset.

Participant Selection for Federated Learning With Heterogeneous Data in Intelligent Transport System

Intelligent Transportation Systems (ITS) utilises the growing trend of both communication technologies and intelligent analytics to make transportation systems more smart and efficient. Federated Learning, a privacy-preserving machine learning paradigm shows promise in being applied in this field. However, the data and device heterogeneity, and highly dynamic environment in ITS pose challenges to the performance of federated learning. One of the recent approaches to address the challenges are to choose proper participants from available clients during training. However, this research field is not fully investigated yet, and many works are still based on the classic random-based selection scheme. In this paper, we present Newt, an enhanced federated learning approach. On one hand, it includes a new client selection utility that explores the trade-off between accuracy performance in each round and system progress. On the other hand, it highlights a feedback control on the selector. Specifically, we implement a control on the selection frequency as a new dimension of client selection method design. We evaluate the proposed system with DNN training tasks on large scale FEMNIST-based datasets that are of different heterogeneity properties. The experiments show that our method outperforms the other baseline methods by as large as 20%.

A Client Selection Method Based on Loss Function Optimization for Federated Learning

Federated learning is a distributed machine learning method that can solve the increasingly serious problem of data islands and user data privacy, as it allows training data to be kept locally and not shared with other users. It trains a global model by aggregating locally-computed models of clients rather than their raw data. However, the divergence of local models caused by data heterogeneity of different clients may lead to slow convergence of the global model. For this problem, we focus on the client selection with federated learning, which can affect the convergence performance of the global model with the selected local models. We propose FedChoice, a client selection method based on loss function optimization, to select appropriate local models to improve the convergence of the global model. It firstly sets selected probability for clients with the value of loss function, and the client with high loss will be set higher selected probability, which can make them more likely to participate in training. Then, it introduces a local control vector and a global control vector to predict the local gradient direction and global gradient direction, respectively, and calculates the gradient correction vector to correct the gradient direction to reduce the cumulative deviation of the local gradient caused by the Non-IID data. We make experiments to verify the validity of FedChoice on CIFAR-10, CINIC-10, MNIST, EMNITS, and FEMNIST datasets, and the results show that the convergence of FedChoice is significantly improved, compared with FedAvg, FedProx, and FedNova.

Microblading Technique for Tattooing of "Hairstrokes" That Simulate Natural Hair: Eyebrow Tattooing and Correction of Medical Conditions.

Microblading is a rapidly expanding technique in cosmetic and medical tattooing, used for eyebrow correction and conditions of hair loss. Tattooing is performed by hand using a special blade; tiny cuts in the outer skin are filled with dark pigment to simulate a natural hair. Indications, the technique, and the microblading procedure step-by-step are considered in what follows. Details on client selection and a range of pitfalls are discussed. The leading application of microblading is cosmetic tattooing of the eyebrows adding pigmented "hairstrokes" to the natural brow area. Tattooed "hairstrokes" fade in color over months and a repeated "touch up" procedure may be required. Pretreatment with laser removal of tattoos of the past may be indicated when a client requests a "touch up" with another brow in another style, shape, or extension. Microblading carries the risk of scarring. The combination with conventional machine-driven needle tattooing for background shading the skin of the brow is also discussed. Microblading is also used as a corrective intervention in a range of dermatological and medical conditions. Having grown exponentially for cosmetic purpose in the first phase of microblading parallel to acquired refinement, the method is now mature and ready to make further progress on medical indication in the coming second phase. The medical community should welcome this opportunity for supplementary correction with restoration of the normal brow anatomy added to other achievements in dermatological and medical therapy.

Tattooing of the Lips by Needle Technique: Artwork and Performance.

Lip tattooing for cosmetic or medical purposes is a difficult operation with indications and contraindications. Lips have a refined microanatomy and many functions ranging from aesthetics and mimics supporting facial expressions to entirely biological functions such as supporting oral functions and servicing sound expression as part of linguistic performance. The anatomy of the lip is explained and illustrated. In lip tattooing, the outlining and enhancement of contour particularly towards the philtrum is important along with keeping symmetry and shape right and as intended. The coloring of the vermilion and dosing of tattoo pigment is another challenge. The article reviews the technical and artistic aspects of lip tattooing down to detail and step by step procedures starting with client selection, strategy planning, and informed consent. Pitfalls and complications are described. When applied as a corrective operation as part of reconstructive plastic surgery, a close cooperation with medical specialists is needed. Lip tattooing appears underrated regarding medical usefulness. The review can be used as a tutorial in the training of newcomers in the field, having a cosmetic or a medical purpose, same technique.

Experimental Evaluation and Analysis of Federated Learning in Edge Computing Environments

Federated learning (FL) is a machine learning system that allows a network of devices to train a model without centralized data. This characteristic makes FL an ideal choice for machine or deep learning using user data while maintaining privacy. Many applications, such as autonomous vehicles that adapt to pedestrian behavior and smart healthcare devices, require machine learning to be performed in edge computing environments. However, the performance of FL in edge computing environments has received limited research attention, and previous studies have not comprehensively evaluated heterogeneity aspects, such as system heterogeneity, statistical heterogeneity, and communication bandwidth. This study aims to fill this research gap by conducting experimental evaluations and detailed analyses of FL in edge computing environments. Specifically, we set up an experimental testbed based on the FL framework on the KubeEdge platform and evaluate the diverse effects of heterogeneity aspects on the model convergence time such as homogeneous versus heterogeneous hardware resources, balanced versus imbalanced data distributions, duplicate versus nonduplicate datasets, client participation ratio at each round, the client selection algorithm, and the communication bandwidth. Overall, this study contributes to the advancement of the field of FL by expanding the understanding of its performance in edge computing environments and providing guidelines for efficient and effective FL systems in heterogeneous environments, which can ultimately benefit various industries and domains.

Personalized federated learning for heterogeneous data: A distributed edge clustering approach.

Federated learning (FL) is a distributed machine learning technique that allows multiple devices (e.g., smartphones and IoT devices) to collaborate in the training of a shared model with each device preserving the privacy of its local data. However, the highly heterogeneous distribution of data among clients in FL can result in poor convergence. In addressing this issue, the concept of personalized federated learning (PFL) has emerged. PFL aims to tackle the effects of non-independent and identically distributed data and statistical heterogeneity and to achieve personalized models with rapid model convergence. One approach is clustering-based PFL, which utilizes group-level client relationships to achieve personalization. However, this method still relies on a centralized approach, whereby the server coordinates all processes. To address these shortcomings, this study introduces a blockchain-enabled distributed edge cluster for PFL (BPFL) that combines the benefits of blockchain and edge computing. Blockchain technology can be used to enhance client privacy and security by recording transactions on immutable distributed ledger networks, thereby improving client selection and clustering. The edge computing system offers reliable storage and computation such that computational processing is locally performed in the edge infrastructure to be closer to clients. Thus, the real-time services and low-latency communication of PFL are improved. However, further work is required to develop a representative dataset for the examination of related types of attacks and defenses for a robust BPFL protocol.

Reputation-Aware Multi-Agent DRL for Secure Hierarchical Federated Learning in IoT

Aiming at protecting device data privacy, Federated Learning (FL) is a framework of distributed machine learning in which devices’ local model parameters are exchanged with a centralized server without revealing the actual data. Hierarchical Federated Learning (HFL) framework was introduced to improve FL communication efficiency where devices are clustered and seek model consensus with the support of edge servers (e.g., base stations). Devices in a cluster submit their local model updates to their assigned local edge server for aggregation at each iteration. The edge servers transmit the aggregated models to a centralized server and establish a global consensus. However, similar to FL, adversaries may threaten the security and privacy of HFL. The client devices within a cluster may deliberately provide unreliable local model updates through poisoning attacks or poor-quality model updates due to inconsistent communication channels, increased device mobility, or inadequate device resources. To address the above challenges, this paper investigates the client selection problem in the HFL framework to eliminate the impact of unreliable clients while maximizing the global model accuracy of HFL. Each FL edge server is equipped with a Deep Reinforcement Learning (DRL)-based reputation model to optimally measure the reliability and trustworthiness of FL workers within its cluster. A Multi-Agent Deep Deterministic Policy Gradient (MADDPG) is utilized to enhance the accuracy and stability of the HFL global model, given the workers’ dynamic behaviors in the HFL environment. The experimental results indicate that our proposed MADDPG improves the accuracy and stability of HFL compared with the conventional reputation model and single-agent DDPG-based reputation model.

Flexible Global Aggregation and Dynamic Client Selection for Federated Learning in Internet of Vehicles

Flexible Global Aggregation and Dynamic Client Selection for Federated Learning in Internet of Vehicles

추억 감성을 활용한 스토리텔링 패션제품 리디자인 기획과 제작

Background/Objectives: This study aims to plan a memory redesign process and produce actual fashion products accordingly.&#x0D; Methods: The methods were literature reviews and case studies. The research papers and Internet sources on storytelling, memory emotion, and redesign were examined. Further, Depth-interviews and production processes were conducted. Through literature research, we defined a concept of storytelling and discovered trend of redesign in the fashion industry. Moreover, we explored the processes and products of design planning cases through storytelling with customers. Fashion brands that specifically revealed the procedures and contents of the work produced through storytelling with customers were selected as the case study by searching “storytelling design” on an Internet portal site using keywords.&#x0D; Results: Based on the study, the memory redesign process was planned as 1) a contest and client selection; 2) memory storytelling involving depth-interview and keyword derivation; 3) design planning involving concept setting and mapping; 4) work creation involving draft presentation, decomposition, and combination; 5) sharing thoughts. Accordingly, the process of recruiting clients and producing memory-sensitive products in person through in-depth interviews of a selected person was revealed, and the individual memory sensibility and redesign method were summarized. The “decomposition and combination” method, which is most widely used in the fashion industry, was used as the redesign technique at the time.&#x0D; Conclusion/Implications: This study focuses on the emotional value of personal memories contained in fashion products. Further, it can expand the area of customization by individuals at the product planning stage and contribute to the development of sustainable fashion sector by redesigning the products that individuals had.

Leveraging heuristic client selection for enhanced secure federated submodel learning

As the number of clients for federated learning (FL) has expanded to the billion level, a new research branch named secure federated submodel learning (SFSL) has emerged. In SFSL, mobile clients only download a tiny ratio of the global model from the coordinator’s global. However, SFSL provides little guarantees on the convergence and accuracy performance as the covered items may be highly biased. In this work, we formulate the problem of client selection through optimizing unbiased coverage of item index set for enhancing SFSL performance. We analyze the NP-hardness of this problem and propose a novel heuristic multi-group client selection framework by jointly optimizing index diversity and similarity. Specifically, heuristic exploration on some random client groups are performed progressively for an empirical approximate solution. Meanwhile, private set operations are used to preserve the privacy of participated clients. We implement the proposal by simulating large-scale SFSL application in a lab environment and conduct evaluations on two real-world data-sets. The results demonstrate the performance (w.r.t., accuracy and convergence speed) superiority of our selection algorithm than SFSL. The proposal is also shown to yield significant computation advantage with similar communication performance as SFSL.

5G-Enabled Distributed Intelligence Based on O-RAN for Distributed IoT Systems

Edge-based distributed intelligence techniques, such as federated learning (FL), have recently been used in many research fields thanks, in part, to their decentralized model training process and privacy-preserving features. However, because of the absence of effective deployment models for the radio access network (RAN), only a tiny number of FL apps have been created for the latest generation of public mobile networks (e.g., 5G and 6G). There is an attempt, in new RAN paradigms, to move toward disaggregation, hierarchical, and distributed network function processing designs. Open RAN (O-RAN), as a cutting-edge RAN technology, claims to meet 5G services with high quality. It includes integrated, intelligent controllers to provide RAN with the power to make smart decisions. This paper proposes a methodology for deploying and optimizing FL tasks in O-RAN to deliver distributed intelligence for 5G applications. To accomplish model training in each round, we first present reinforcement learning (RL) for client selection for each FL task and resource allocation using RAN intelligence controllers (RIC). Then, a slice is allotted for training depending on the clients chosen for the task. Our simulation results show that the proposed method outperforms state-of-art FL methods, such as the federated averaging algorithm (FedAvg), in terms of convergence and number of communication rounds.