Dynamic Client Research Articles

RFCSC: Communication efficient reinforcement federated learning with dynamic client selection and adaptive gradient compression

In the field of public safety, high-quality data is often owned by governments, companies, and organizations, making it difficult to train effective models through centralized datasets. This paper leverages federated learning as a mechanism to address data privacy concerns. Within the federated learning framework, the data across different clients is typically Non-IID (non-Independently and Identically Distributed). Furthermore, The complexity of sensitive image recognition tasks in public safety, along with the large number of model parameters, can lead to communication congestion issues in federated learning. To solve these challenges, this paper proposes a Reinforcement Federated Client Selection and Gradient Compression Method(RFCSC). By integrating client data prototypes with accuracy metrics, we dynamically assess the contribution of each client in federated learning. Through an intelligent dynamic incentive mechanism based on reinforcement learning, high-quality client nodes are dynamically selected to participate in federated learning, achieving dynamic adaptive aggregation, reducing the influence of Non-IID data, reducing communication cost, enhancing model accuracy, and achieving a balance between quality and efficiency. To address the issue of high communication cost for parameter transmission, we propose an adaptive model compression strategy in reinforcement federated learning which make local clients find an appropriate compression rate. This approach not only reduces gradient communication overhead but also minimizes the impact of compression on model accuracy. The effectiveness of our proposed approach are corroborated through comprehensive experiments conducted on one private dataset and two public datasets.

Secure Dynamic Scheduling for Federated Learning in Underwater Wireless IoT Networks

Federated learning (FL) is a distributed machine learning approach that can enable Internet of Things (IoT) edge devices to collaboratively learn a machine learning model without explicitly sharing local data in order to achieve data clustering, prediction, and classification in networks. In previous works, some online multi-armed bandit (MAB)-based FL frameworks were proposed to enable dynamic client scheduling for improving the efficiency of FL in underwater wireless IoT networks. However, the security of online dynamic scheduling, which is especially essential for underwater wireless IoT, is increasingly being questioned. In this work, we study secure dynamic scheduling for FL frameworks that can protect against malicious clients in underwater FL-assisted wireless IoT networks. Specifically, in order to jointly optimize the communication efficiency and security of FL, we employ MAB-based methods and propose upper-confidence-bound-based smart contracts (UCB-SCs) and upper-confidence-bound-based smart contracts with a security prediction model (UCB-SCPs) to address the optimal scheduling scheme over time-varying underwater channels. Then, we give the upper bounds of the expected performance regret of the UCB-SC policy and the UCB-SCP policy; these upper bounds imply that the regret of the two proposed policies grows logarithmically over communication rounds under certain conditions. Our experiment shows that the proposed UCB-SC and UCB-SCP approaches significantly improve the efficiency and security of FL frameworks in underwater wireless IoT networks.

Multi-Agent Proximal Policy Optimization-Based Dynamic Client Selection for Federated AI in 6G-Oriented Internet of Vehicles

Multi-Agent Proximal Policy Optimization-Based Dynamic Client Selection for Federated AI in 6G-Oriented Internet of Vehicles

Dynamic Client Scheduling Enhanced Federated Learning for UAVs

Dynamic Client Scheduling Enhanced Federated Learning for UAVs

Leveraging Human-in-the-Loop Engagement Through AI in Web Design Education: A Case Study on Adapting to Dynamic Client Requirements

Leveraging Human-in-the-Loop Engagement Through AI in Web Design Education: A Case Study on Adapting to Dynamic Client Requirements

AFL-DCS: An asynchronous federated learning framework with dynamic client scheduling

The emerging federated learning is a distributed machine learning paradigm which enables training a global model on a massive number of edge devices while protecting the privacy of local data. In the typical federated learning paradigm, the global model is updated with a synchronized protocol, which requires the server to wait for all clients to return their model parameters before updating the global model in each round. However, the straggler effect due to heterogeneous devices may cause a serious degradation in the training efficiency of synchronous federated learning. Asynchronous federated learning can effectively alleviate the inefficiency of training caused by heterogeneous devices, but the asynchronous update protocol makes the global model more vulnerable to heterogeneous data. The global model of asynchronous federated learning may be difficult to converge or even not under non-IID settings. In this paper, we propose an asynchronous federated learning framework with dynamic client scheduling (AFL-DCS) to mitigate the negative impact of data heterogeneity and dynamic clients. By dynamically clustering clients, AFL-DCS can effectively handle the dynamic check-in clients and their non-IID data. We evaluate AFL-DCS on three datasets (MNIST, FashionMNIST and CIFAR-10) under several different types of non-IID settings and compare AFL-DCS with typical asynchronous federated learning frameworks. Experimental results show that AFL-DCS can reduce the number of communication rounds by up to 39.0%, 52.4% and 89.6% on average, and reduce the accuracy variance by up to 88.9%, 80.0% and 76.8% on average, respectively, which confirms that our framework can significantly enhance the learning efficiency, model performance and stability of asynchronous federated learning under various non-IID settings.

Federated Dynamic Client Selection for Fairness Guarantee in Heterogeneous Edge Computing

Federated Dynamic Client Selection for Fairness Guarantee in Heterogeneous Edge Computing

An Improved Big Data Analytics Architecture Using Federated Learning for IoT-Enabled Urban Intelligent Transportation Systems

The exponential growth of the Internet of Things has precipitated a revolution in Intelligent Transportation Systems, notably in urban environments. An ITS leverages advancements in communication technologies and data analytics to enhance the efficiency and intelligence of transport networks. At the same time, these IoT-enabled ITSs generate a vast array of complex data classified as Big Data. Traditional data analytics frameworks need help to efficiently process these Big Data due to its sheer volume, velocity, variety, and significant data privacy concerns. Federated Learning, known for its privacy-preserving attributes, is a promising technology for implementation within ITSs for IoT-generated Big Data. Nevertheless, the system faces challenges due to the variable nature of devices, the heterogeneity of data, and the dynamic conditions in which ITS operates. Recent efforts to mitigate these challenges focus on the practical selection of an averaging mechanism during the server’s aggregation phase and practical dynamic client training. Despite these efforts, existing research still relies on personalized FL with personalized averaging and client training. This paper presents a personalized architecture, including an optimized Federated Averaging strategy that leverages FL for efficient and real-time Big Data analytics in IoT-enabled ITSs. Various personalization methods are applied to enhance the traditional averaging algorithm. Local fine-tuning and weighted averaging tailor the global model to individual client data. Custom learning rates are utilized to boost the performance further. Regular evaluations are advised to maintain model efficacy. The proposed architecture addresses critical challenges like real-life federated environment settings, data integration, and significant data privacy, offering a comprehensive solution for modern urban transportation systems using Big Data. Using the Udacity Self-Driving Car Dataset foe vehicle detection, we apply the proposed approaches to demonstrate the efficacy of our model. Our empirical findings validate the superiority of our architecture in terms of scalability, real-time decision-making capabilities, and data privacy preservation. We attained accuracy levels of 93.27%, 92.89%, and 92.96% for our proposed model in a Federated Learning architecture with 10 nodes, 20 nodes, and 30 nodes, respectively.

Ultrasmall Gold Nanoparticles as Clients of Biomolecular Condensates.

Liquid-liquid phase separation (LLPS) of biopolymers to form condensates is a widespread phenomenon in living cells. Agents that target or alter condensation can help uncover elusive physiological and pathological mechanisms. Owing to their unique material properties and modes of interaction with biomolecules, nanoparticles represent attractive condensate-targeting agents. Our work focused on elucidating the interaction between ultrasmall gold nanoparticles (usGNPs) and diverse types of condensates of tau, a representative phase-separating protein associated with neurodegenerative disorders. usGNPs attract considerable interest in the biomedical community due to unique features, including emergent optical properties and good cell penetration. We explored the interaction of usGNPs with reconstituted self-condensates of tau, two-component tau/polyanion and three-component tau/RNA/alpha-synuclein coacervates. The usGNPs were found to concentrate into condensed liquid droplets, consistent with the formation of dynamic client (nanoparticle) - scaffold (tau) interactions, and were observable thanks to their intrinsic luminescence. Furthermore, usGNPs were capable to promote LLPS of a protein domain which is unable to phase separate on its own. Our study demonstrates the ability of usGNPs to interact with and illuminate protein condensates. We anticipate that nanoparticles will have broad applicability as nanotracers to interrogate phase separation, and as nanoactuators controlling the formation and dissolution of condensates.

Fine-Grained Access Control with User Revocation in Smart Manufacturing

Collaborative manufacturing is a key enabler of Industry 4.0 that requires secure data sharing among multiple parties. However, intercompany data-sharing raises important privacy and security concerns, particularly given intellectual property and business-sensitive information collected by many devices. In this paper, we propose a solution that combines four technologies to address these challenges: Attribute-Based Encryption for data access control, blockchain for data integrity and non-repudiation, Hardware Security Modules for authenticity, and the Interplanetary File System for data scalability. We also use OpenID for dynamic client identification and propose a new method for user revocation in Attribute-Based Encryption. Our evaluation shows that the solution can scale up to 2,000,000 clients while maintaining all security guarantees.

Learning-based client selection for multiple federated learning services with constrained monetary budgets

We investigate a data quality-aware dynamic client selection problem for multiple federated learning (FL) services in a wireless network, where each client offers dynamic datasets for the simultaneous training of multiple FL services, and each FL service demander has to pay for the clients under constrained monetary budgets. The problem is formalized as a non-cooperative Markov game over the training rounds. A multi-agent hybrid deep reinforcement learning-based algorithm is proposed to optimize the joint client selection and payment actions, while avoiding action conflicts. Simulation results indicate that our proposed algorithm can significantly improve training performance.

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

Attribute Based Data Management In Crypt Cloud

Data owners will store their data publicly cloud together with encryption andspecific arrangement of traits to get to control on the cloud information. While moving the information into an open cloud they will designate some credit set to their data. In case any endorsed cloud customer has to download the data they need to enter that particular credits set to perform further exercises on data owner's data. A cloud client needs to enroll their subtleties under the haze association to get to the information proprietor's information. Clients need to present their subtleties as characteristics along with their assignment. Considering the customer nuances Semi-Trusted Authority produces disentangling keys to comprehend power on owner'sinformation. A cloud user wants to register their details under the cloud organization to access the info owner’s data. Users want to submit their details as attributes together with their designation. In light of the client subtleties Semi-Trusted Authority produces decoding keys to understand power on proprietor's information. A client can playan honest deal of tasks over the cloud information. Within the event that the client possesses to peruse the cloud information he should enter some read related traits, and on the off chance that he possesses to compose the knowledge he should enter compose related qualities. For each and every dynamic client in an incredibly organization would be confirmed with their novel trait set. These ascribes would be shared by the administrators to the approved clients in the cloud association Sepulcher DAC authorizes dynamic access control that has productivity, since it doesn't need costly disentangling, re-encryption and moving/re-moving of monster data at the regulator side, and security since itdoesn't require expensive decoding, re-encryption and transferring/re-transferring of giant information at the overseer side, and security because it quickly denies getting to authorizations.

Dynamic Federated Learning for GMEC With Time-Varying Wireless Link

Smart grid applications, such as predicting energy consumption, grid user behavior analysis and predicting energy theft, etc., are data-driven applications that require machine learning with a wealth of data generated from Internet of Things (IoT) based metering devices. However, traditional methods of uploading this huge data to the remote cloud for data analytics may be low efficient due to the non-negligible network transmission delay. By deploying a number of computing-enabled devices at the network edge, edge computing supports the implementation of machine learning close to the power grid environment. Considering the limited computing resources of edge devices and non-independent and identical (non-IID) data source, federated learning is a feasible edge computing based machine learning model. In federated learning, distributed mobile clients and a federated server collaborate to perform machine learning. Generally, the more clients to join the federated learning, the faster to obtain learning convergence and the higher resource utility. However, the communications between clients and the server in training rounds of federated learning may fail due to time-varying link reliability properties in a wireless network of smart grid, which not only slows down the model convergence rate but also wastes resources, such as energy consumption for invalid local training. This paper studies a dynamic federated learning problem in a power grid mobile edge computing (GMEC) environment, considering the high dynamic of link reliability. We design a delay deadline constrained federated learning framework to avoid extremely long training delay, and then formulate a dynamic client selection problem for computing utility maximization in such learning framework. Two online client selection algorithms, including cli-max greedy and uti-positive guarantee , are proposed to address the problem. The theoretical analysis and simulation results are conducted to illustrate the efficiency of the proposal.

Smart kills and worthless deaths: eSports analytics for League of Legends

AbstractVast data on eSports should be easily accessible but often is not. League of Legends (LoL) only has rudimentary statistics such as levels, items, gold, and deaths. We present a new way to capture more useful data. We track every champion’s location multiple times every second. We track every ability cast and attack made, all damages caused and avoided, vision, health, mana, and cooldowns. We track continuously, invisibly, remotely, and live. Using a combination of computer vision, dynamic client hooks, machine learning, visualization, logistic regression, large-scale cloud computing, and fast and frugal trees, we generate this new high-frequency data on millions of ranked LoL games, calibrate an in-game win probability model, develop enhanced definitions for standard metrics, introduce dozens more advanced metrics, automate player improvement analysis, and apply a new player-evaluation framework on the basic and advanced stats. How much does an individual contribute to a team’s performance? We find that individual actions conditioned on changes to estimated win probability correlate almost perfectly to team performance: regular kills and deaths do not nearly explain as much as smart kills and worthless deaths. Our approach offers applications for other eSports and traditional sports. All the code is open-sourced.

Shielding Collaborative Learning: Mitigating Poisoning Attacks through Client-Side Detection

Collaborative learning allows multiple clients to train a joint model without sharing their data with each other. Each client performs training locally and then submits the model updates to a central server for aggregation. Since the server has no visibility into the process of generating the updates, collaborative learning is vulnerable to poisoning attacks where a malicious client can generate a poisoned update to introduce backdoor functionality to the joint model. The existing solutions for detecting poisoned updates, however, fail to defend against the recently proposed attacks, especially in the non-IID (independent and identically distributed) setting. In this article, we present a novel defense scheme to detect anomalous updates in both IID and non-IID settings. Our key idea is to realize client-side cross-validation, where each update is evaluated over other clients’ local data. The server will adjust the weights of the updates based on the evaluation results when performing aggregation. To adapt to the unbalanced distribution of data in the non-IID setting, a dynamic client allocation mechanism is designed to assign detection tasks to the most suitable clients. During the detection process, we also protect the client-level privacy to prevent malicious clients from knowing the participations of other clients, by integrating differential privacy with our design without degrading the detection performance. Our experimental evaluations on three real-world datasets show that our scheme is significantly robust to two representative poisoning attacks.

Justin Richer on OAuth

In Episode 376 of “Software Engineering Radio,” Justin Richer, lead author of OAuth2 in Action and editor of OAuth extensions RFC 7591, 7592, and 7662, discusses the key technical features of the OAuth 2.0 protocol for authorization. Gavin Henry spoke with Richer about browser-based OAuth2, types of tokens, OpenID Connect, PKCE, JavaScript Object Notation Web Token pros and cons, where to store them, client secrets, single-page apps, mobile apps, current best practices, OAuth.XYZ, HEART, MITREid, token validation, dynamic client registration, the decision factors of the various types of authorization grants to use, and what is next for OAuth. To hear the full interview, visit http://www.se-radio.net or access our archives via RSS at http:// feeds.feedburner.com/se-radio.

Hsp90 Chaperones Bluetongue Virus Proteins and Prevents Proteasomal Degradation.

The molecular chaperone machinery is important for the maintenance of protein homeostasis within the cells. The principle activities of the chaperone machinery are to facilitate protein folding and organize conformationally dynamic client proteins. Prominent among the members of the chaperone family are heat shock protein 70 (Hsp70) and 90 (Hsp90). Like cellular proteins, viral proteins depend upon molecular chaperones to mediate their stabilization and folding. Bluetongue virus (BTV), which is a model system for the Reoviridae family, is a nonenveloped arbovirus that causes hemorrhagic disease in ruminants. This constitutes a significant burden upon animals of commercial significance, such as sheep and cattle. Here, for the first time, we examined the role of chaperone proteins in the viral lifecycle of BTV. Using a combination of molecular, biochemical, and microscopic techniques, we examined the function of Hsp90 and its relevance to BTV replication. We demonstrate that Hsp70, the chaperone that is commonly usurped by viral proteins, does not influence virus replication, while Hsp90 activity is important for virus replication by stabilizing BTV proteins and preventing their degradation via the ubiquitin-proteasome pathway. To our knowledge this is the first report showing the involvement of Hsp90 as a modulator of BTV infection.IMPORTANCE Protein chaperones are instrumental for maintaining protein homeostasis, enabling correct protein folding and organization; prominent members include heat shock proteins 70 and 90. Virus infections place a large burden on this homeostasis. Identifying and understanding the underlying mechanisms that facilitate Bluetongue virus replication and spread through the usurpation of host factors is of primary importance for the development of intervention strategies. Our data identify and show that heat shock protein 90, but not heat shock protein 70, stabilizes bluetongue virus proteins, safeguarding them from proteasomal degradation.

Managing the Competitiveness of the Enterprise in the Context of Transformational Change

Most enterprises currently regard customer loyalty as the primary tool for increasing their competitiveness (from among non-price methods). To test the theoretical results of the study, a dynamic client base management model was developed for a enterprise in the real sector of the economy, and on the basis of this model, a strategy was found to optimally manage the enterprise's client base over an interval of 12 months, which would maximize the long-term cost of the client base. The control effect found using the gradient descent method, along with optimization of the company's expenses and improvement of the customer base's efficiency, will simultaneously allow you to control not individual clients, but groups of clients of the enterprise in accordance with the model developed in this study, adapted for groups of clients; to take into account differences in the customer behavior of customers and to track changes in the quality characteristics of the customer base. All this allows to increase the competitiveness of the enterprise significantly.

Managing the Competitiveness of the Enterprise in the Context of Transformational Change

Most enterprises currently regard customer loyalty as the primary tool for increasing their competitiveness (from among non-price methods). To test the theoretical results of the study, a dynamic client base management model was developed for a enterprise in the real sector of the economy, and on the basis of this model, a strategy was found to optimally manage the enterprise's client base over an interval of 12 months, which would maximize the long-term cost of the client base. The control effect found using the gradient descent method, along with optimization of the company's expenses and improvement of the customer base's efficiency, will simultaneously allow you to control not individual clients, but groups of clients of the enterprise in accordance with the model developed in this study, adapted for groups of clients; to take into account differences in the customer behavior of customers and to track changes in the quality characteristics of the customer base. All this allows to increase the competitiveness of the enterprise significantly.