检索结果-内蒙古大学图书馆

Multi-index federated aggregation algorithm based on trusted verification

CCF TRANSACTIONS ON HIGH PERFORMANCE COMPUTING 2024年第6期6卷 632-645页

作者： Zhenshan, Bao Mengyuan, Wang Bai, Wei Wenbo, Zhang Beijing Univ Technol Coll Comp Sci Beijing 100124 Peoples R China

Motivated by the modern phenomenon of distributed data collected by edge devices at scale, federated learning can use large amounts of training data from diverse users for better representation and generalization. To improve flexibility and scalability, a new federated optimization algorithm, named multi-index federated aggregation algorithm based on trusted verification (TVFedmul) is proposed. It overcomes a series of problems caused by the original aggregation algorithm, which only takes the single index of data quantity as a reference factor to measure the aggregation weight of each client. The improved algorithm is based on multi-index measurement. It reflects the comprehensive ability of clients more thoroughly, to make overall judgments. Further, to achieve customized federated learning, a hyperparameter alpha is introduced. It can be changed to determine the importance of indexes. Finally, via extensive experimentation, it has been observed that the improved algorithm is faster, and the accuracy reaches 94.59%, which is 2.53% higher than that of FedAvg (92.06%).

关键词： Federated learning aggregation algorithm Distributed learning

来源：评论

学校读者我要写书评

暂无评论

Multi-index Federated aggregation algorithm Based on Trusted Verification 22nd

Multi-index Federated Aggregation Algorithm Based on Trusted...

引用

22nd International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT 2021)

作者： Bao, Zhenshan Bai, Wei Zhang, Wenbo Beijing Univ Technol Fac Informat Technol Beijing 100124 Peoples R China

ISBN: (纸本)9783030967727;9783030967710

Movited by the modern phenomenon of distributed data collected by edge devices at scale, federated learning can use the large amounts of training data from diverse users for better representation and generalization. To improve flexibility and scalability, we propose a new federated optimization algorithm, named as Multi-index federated aggregation algorithm based on trusted verfication(TVFedmul). TVFedmul is optimized based on Fedavg algorithm, which overcomes a series of problems caused by the original aggregation algorithm, which only takes the single index of data quantity as a reference factor to measure the aggregation weight of each client. The improved aggregation algorithm is based on multi-index measurement, which can reflect the comprehensive ability of clients more comprehensively, so as to make overall judgment. Further, we introduces hyperparameter alpha, which can be changed to determine the importance of the indexes. Finally, via extensive experimentation, the efficiency and effectiveness of the proposed algorithm is verified.

关键词： Federated learning aggregation algorithm Distributed learning

来源：评论

学校读者我要写书评

暂无评论

Data aggregation algorithm of Sensor Network Nodes for Health Monitoring Based on Fuzzy Clustering

引用

JOURNAL OF TESTING AND EVALUATION 2021年第1期51卷 13-13页

作者： Liang, Shujun Cheng, Jing Zhang, Jianwei Zhengzhou Univ Light Ind Software Engn Coll Zhengzhou 450002 Peoples R China Zhengzhou Univ Light Ind Engn Training Ctr Zhengzhou 450002 Peoples R China

Wireless human body sensor networks are widely used, but because of hardware and environmental constraints, their nodes have problems such as unsustainable energy and weak computing capabilities. To further improve the efficiency of data aggregation for health monitoring, a fuzzy clustering based data aggregation algorithm is presented. Based on the fuzzy clustering algorithm of distributed wireless sensors, this work analyzes the processing mechanism of distributed data and introduces an optimal weighted weighting algorithm, thereby obtaining the optimal weight distribution coefficient of each sensor, results of node variance evaluation, and corresponding data aggregation through distributed data processing. The proposed algorithm is of great significance to improve the accuracy of data collection and reduce the overall energy consumption of the network.

关键词： fuzzy clustering wireless sensor network node aggregation algorithm health monitoring

来源：评论

学校读者我要写书评

暂无评论

FedBayes: An aggregation Method for Federated Learning that uses Bayesian Regression 28

FedBayes: An Aggregation Method for Federated Learning that ...

引用

28th International Conference on System Theory Control and Computing

作者： Bejenar, Iuliana Ferariu, Lavinia Pascal, Carlos Caruntu, Constantin F. Gheorghe Asachi Tech Univ Iasi Dept Automat Control & Appl Informat Iasi Romania

ISBN: (纸本)9798350364309;9798350364293

Over the years, the concept of Federated Learning (FL) has gained popularity based on compliance with the General Data Protection Regulation (GDPR). This framework allows multiple participants to collaborate on training a shared global model, without exchanging training samples. In real-world applications, the data of different participants are usually nonindependently and identically distributed (non-IID);in these cases, the clients are vulnerable to producing biased local models, for which FL-based aggregation could be improper. Several problems may also arise when some clients work with an insufficient amount of data or are exposed to potential attacks. To address these main issues, this paper proposes a new algorithm that evaluates the accuracy of models derived from participating clients and uses Bayesian regression to aggregate the local models. Through this strategy, the number of clients who can negatively affect the global model can be reduced, whether they have been attacked or have obtained poor performance for other reasons (e.g., an insufficient amount of data). The experiments are performed using a previously proposed algorithm, FedAccSize, together with this new extension, FedBayes. In the considered scenarios, both independent and identically distributed data (IID) and non-IID data are used to demonstrate the ability of the proposed algorithms to obtain an aggregation of the global model which can be done safely. Based on the comparison with the established algorithms FedAvg and FedAvgM, it results that assessing the quality of the local models is crucial for aggregation.

关键词： federated learning Bayesian regression collaboration aggregation algorithm non-IID data

来源：评论

学校读者我要写书评

暂无评论

Securing the collective intelligence: a comprehensive review of federated learning security attacks and defensive strategies

引用

KNOWLEDGE AND INFORMATION SYSTEMS 2025年第4期67卷 3099-3137页

作者： Kaushal, Vishal Sharma, Sangeeta Natl Inst Technol Comp Sci & Engn Dept Hamirpur 177005 Himachal Prades India

Federated learning holds significant potential as a collaborative machine learning technique, allowing multiple entities to work together on a collective model without the need to exchange data. However, due to the distribution of data across multiple devices, federated learning becomes susceptible to a range of attacks. This paper provides an extensive examination of the different forms of attacks that can target federated learning systems. The attacks discussed include data poisoning attacks, model poisoning attacks, backdoor attacks, Byzantine attacks, membership inference attacks, model inversion attacks, etc. Each attack is examined in detail, with examples from the literature provided. Additionally, potential countermeasures to defend against these attacks are explored. The objective of this review is to provide an in-depth survey of the current landscape in federated learning attacks and corresponding defense mechanisms.

关键词： Centralized learning Federated learning Threats Defense aggregation algorithm

来源：评论

学校读者我要写书评

暂无评论

A robust federated learning algorithm for partially trusted environments

引用

COMPUTERS & SECURITY 2025年 148卷

作者： Li, Yong Liu, TongTong Ling, HaiChao Du, Wei Ren, XiangLin Changchun Univ Technol Sch Comp Sci & Engn Changchun 130012 Peoples R China Changchun Univ Technol AI Res Inst Changchun 130012 Peoples R China Jilin Univ Sch Comp Sci & Technol Changchun 130012 Peoples R China Shandong Xiehe Univ Coll Comp Jinan 250107 Peoples R China

Due to the distributed nature of federated learning, it is vulnerable to poisoning attacks during the training process. The model's resistance to poisoning attacks can be improved using robust aggregation algorithms. Current research on federated learning to resist poisoning attacks is mainly based on two settings: No trust or Byzantine robustness. However, both settings are not close enough to reality in practical scenarios. In many practical applications, some participants in federated learning are trustworthy. For example, participants who have participated in the training of this model before and performed very well, or participants with strong compliance and credibility such as governments and some national agencies participate in the training. In existing research, these trusted participants still have to accept the judgment of the aggregation node, which generates unnecessary computation, increases overhead, and does not take advantage of a trusted environment. Since there is no attack behavior on the trusted client, its training results are used to classify the trustworthiness of other untrusted clients and identify attack nodes with higher accuracy. Therefore, this paper proposes a robust federated learning algorithm for partially trusted environments. The proposed scheme uses the experimental results of trusted clients to judge the behavior of untrustworthy clients by the cosine similarity and the Local Outlier Factor and further identify and detect malicious clients. Experiments are performed on MNIST and CIFAR datasets. Comparison with other six aggregation algorithms under 30% attack scenario. And compared with the other four aggregation algorithms under 70% attack conditions. Our algorithm is more accurate than almost all of the other aggregation algorithms. The paper is the first to conduct robust research on federated learning in a partially trusted environment, and the proposed algorithm can more effectively resist poisoning attacks.

关键词： Federated learning Robustness aggregation algorithm Partially trusted environments Poisoning attack

来源：评论

学校读者我要写书评

暂无评论

Prediction of Locally Stationary Data Using Expert Advice

引用

PROBLEMS OF INFORMATION TRANSMISSION 2024年第1期60卷 35-52页

作者： V'yugin, V. V. Trunov, V. G. Zukhba, R. D. Russian Acad Sci Kharkevich Inst Informat Transmiss Problems Moscow Russia Moscow Inst Phys & Technol Moscow Russia

We address the lifelong machine learning problem. Within the game-theoretic approach, in the calculation of the next prediction we use no assumptions on the stochastic nature of a source that generates the data flow: the source can be either analog, or algorithmic, or probabilistic;its parameters can change at random times;when constructing a prediction model, only structural assumptions are used about the nature of data generation. We present an online forecasting algorithm for a locally stationary time series. We also obtain an estimate for the efficiency of the proposed algorithm. The obtained estimates for the regret of the algorithm are illustrated by results of numerical experiments.

关键词： lifelong machine learning predictive algorithms supervised learning adaptive online forecasting algorithms predictions with expert advice regret aggregation algorithm Fixed Share method Mixing Past Posteriors (MPP) method

来源：评论

学校读者我要写书评

暂无评论

Enhancing Human Activity Recognition With FedPA: Focusing on Non-IID Data Challenges in Federated Learning

引用

IEEE SENSORS JOURNAL 2024年第23期24卷 39230-39242页

作者： Wen, Xiaoxu Wang, Yan Yuan, Menghao Geng, Yingrui Yu, Hongnian Zheng, Ge Zhongyuan Univ Technol Sch Automat & Elect Engn Zhengzhou 450007 Peoples R China Edinburgh Napier Univ Sch Comp Engn & Built Environm Edinburgh EH10 5DT Midlothian Scotland Univ Cambridge Dept Engn Cambridge CB2 1TN England

Federated learning (FL) revolutionizes distributed learning in human activity recognition (HAR) by allowing clients to train models locally and share only model parameters, thus optimizing data usage and mitigating privacy concerns. However, the presence of nonindependent and identically distributed (Non-IID) data across clients impedes FL efficiency between the server and clients, affecting HAR performance and communication efficiency. Acknowledging the significance of posttraining parameters as intrinsic representations of knowledge acquired by client models, we introduce federated parameters averaging (FedPA), a novel algorithm for model aggregation. This algorithm strategically assigns varying weight coefficients to clients during aggregation, accurately reflecting each client's learning contribution and thereby enhancing the efficacy of both global and client models. We conducted empirical analyses using real-world datasets to assess FedPA's effectiveness. The results demonstrate that FedPA not only preserves accuracy but also improves communication efficiency compared to existing FL aggregation algorithms, like FedAvg, FedMA, and FedCDA. These findings underscore FedPA's superiority in addressing Non-IID challenges in HAR tasks and highlight its potential to improve overall model performance in FL settings.

关键词： aggregation algorithm federated learning (FL) human activity recognition (HAR) nonindependent and identically distributed (Non-IID) data

来源：评论

学校读者我要写书评

暂无评论

Online aggregation of Probabilistic Predictions of Hourly Electrical Loads

引用

JOURNAL OF COMMUNICATIONS TECHNOLOGY AND ELECTRONICS 2022年第6期67卷 702-716页

作者： V'yugin, V. V. Trunov, V. G. Russian Acad Sci Kharkevich Inst Informat Transmiss Problems Moscow 127051 Russia

In this paper, we consider the problem of online probabilistic time series forecasting. The difference between a probabilistic prediction (distribution function) and a numerical outcome is measured using a loss function (scoring rule). In practical statistics, the Continuous Ranked Probability Score (CRPS) rule is often used to estimate the discrepancy between probabilistic predictions and quantitative outcomes. Here, we consider the case when several competing methods (experts) give their predictions in the form of distribution functions. Expert predictions are provided with confidence levels. We propose an algorithm for online aggregation of these distribution functions with allowance for the confidence levels to expert forecasts. The discounted error of the proposed algorithm with allowance for the confidence levels is estimated in the form of a comparison of the cumulative losses of the algorithm and the losses of experts. A technology for constructing predictive expert algorithms and aggregating their probabilistic predictions using the example of the problem of predicting electricity consumption 1 or more hours ahead was developed. The results of numerical experiments using real data are presented.

关键词： Keywords predictions with expert advice online probabilistic prediction regret confidence levels aggregation algorithm continuous ranked probability scoring rule CRPS

来源：评论

学校读者我要写书评

暂无评论

A Shapley value-enhanced evaluation technique for effective aggregation in Federated Learning

A Shapley value-enhanced evaluation technique for effective ...

引用

IEEE Future Networks World Forum (FNWF)

作者： Salarbashishahri, Mohammadreza Okegbile, Samuel D. Cai, Jun Concordia Univ Dept Elect & Comp Engn Montreal PQ Canada

ISBN: (纸本)9781665462501

5G networks make it possible to transfer real-time sensory data between millions of devices, forming the internet of things. A typical method to utilize these data is to train a machine learning algorithm to extract the features. Federated learning (FL) is a platform for a coalition of clients to train a model collaboratively without sharing their data to preserve data privacy. Data and model poisoning attacks, free-riding attacks, and model divergence due to clients' non-independent and identically distributed (non-IID) datasets are some challenges in conventional federated learning. The lack of an evaluation method in federated averaging (FedAvg) in FL makes it impossible to identify malicious users or amend the divergence of the global model. In this study, we propose a Shapley-based aggregation algorithm called Shapley averaging (ShapAvg) to aggregate the global model more effectively by evaluating the clients' models. In this algorithm, each client's weight in the weighted average will be proportional to its contribution to the global model performance. The results show that the proposed method outperforms FedAvg when using non-IID datasets and in case of data poisoning or free-riding attacks.

关键词： aggregation algorithm contribution evaluation federated learning Shapley value

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：