A new nonlinear algorithm is proposed for strapdown inertial navigation system （SINS）/celestial navigation system （CNS）/global positioning system （GPS） integrated navigation systems. The algorithm employs a nonl...A new nonlinear algorithm is proposed for strapdown inertial navigation system （SINS）/celestial navigation system （CNS）/global positioning system （GPS） integrated navigation systems. The algorithm employs a nonlinear system error model which can be modified by unscented Kalman filter （UKF） to give predictions of local filters. And these predictions can be fused by the federated Kalman filter. In the system error model, the rotation vector is introduced to denote vehicle＇s attitude and has less variables than the quaternion. Also, the UKF method is simplified to estimate the system error model, which can both lead to less calculation and reduce algorithm implement time. In the information fusion section, a modified federated Kalman filter is proposed to solve the singular covariance problem. Specifically, the new algorithm is applied to maneuvering vehicles, and simulation results show that this algorithm is more accurate than the linear integrated navigation algorithm.展开更多
As the 5G communication networks are being widely deployed worldwide,both industry and academia have started to move beyond 5G and explore 6G communications.It is generally believed that 6G will be established on ubiq...As the 5G communication networks are being widely deployed worldwide,both industry and academia have started to move beyond 5G and explore 6G communications.It is generally believed that 6G will be established on ubiquitous Artificial Intelligence(AI)to achieve data-driven Machine Learning(ML)solutions in heterogeneous and massive-scale networks.However,traditional ML techniques require centralized data collection and processing by a central server,which is becoming a bottleneck of large-scale implementation in daily life due to significantly increasing privacy concerns.Federated learning,as an emerging distributed AI approach with privacy preservation nature,is particularly attractive for various wireless applications,especially being treated as one of the vital solutions to achieve ubiquitous AI in 6G.In this article,we first introduce the integration of 6G and federated learning and provide potential federated learning applications for 6G.We then describe key technical challenges,the corresponding federated learning methods,and open problems for future research on federated learning in the context of 6G communications.展开更多
Multi-agent systems can solve scientific issues related to complex systems that are difficult or impossible for a single agent to solve through mutual collaboration and cooperation optimization.In a multi-agent system...Multi-agent systems can solve scientific issues related to complex systems that are difficult or impossible for a single agent to solve through mutual collaboration and cooperation optimization.In a multi-agent system,agents with a certain degree of autonomy generate complex interactions due to the correlation and coordination,which is manifested as cooperative/competitive behavior.This survey focuses on multi-agent cooperative optimization and cooperative/non-cooperative games.Starting from cooperative optimization,the studies on distributed optimization and federated optimization are summarized.The survey mainly focuses on distributed online optimization and its application in privacy protection,and overviews federated optimization from the perspective of privacy protection me-chanisms.Then,cooperative games and non-cooperative games are introduced to expand the cooperative optimization problems from two aspects of minimizing global costs and minimizing individual costs,respectively.Multi-agent cooperative and non-cooperative behaviors are modeled by games from both static and dynamic aspects,according to whether each player can make decisions based on the information of other players.Finally,future directions for cooperative optimization,cooperative/non-cooperative games,and their applications are discussed.展开更多
Since the beginning of the 21 st century,the geoscience research has been entering a significant transitional period with the establishment of a new knowledge system as the core and with the drive of big data as the m...Since the beginning of the 21 st century,the geoscience research has been entering a significant transitional period with the establishment of a new knowledge system as the core and with the drive of big data as the means.It is a revolutionary leap in the research of geoscience knowledge discovery from the traditional encyclopedic discipline knowledge system to the computer-understandable and operable knowledge graph.Based on adopting the graph pattern of general knowledge representation,the geoscience knowledge graph expands the unique spatiotemporal features to the Geoscience knowledge,and integrates geoscience knowledge elements,such as map,text,and number,to establish an all-domain geoscience knowledge representation model.A federated,crowd intelligence-based collaborative method of constructing the geoscience knowledge graph is developed here,which realizes the construction of high-quality professional knowledge graph in collaboration with global geo-scientists.We also develop a method for constructing a dynamic knowledge graph of multi-modal geoscience data based on in-depth text analysis,which extracts geoscience knowledge from massive geoscience literature to construct the latest and most complete dynamic geoscience knowledge graph.A comprehensive and systematic geoscience knowledge graph can not only deepen the existing geoscience big data analysis,but also advance the construction of the high-precision geological time scale driven by big data,the compilation of intelligent maps driven by rules and data,and the geoscience knowledge evolution and reasoning analysis,among others.It will further expand the new directions of geoscience research driven by both data and knowledge,break new ground where geoscience,information science,and data science converge,realize the original innovation of the geoscience research and achieve major theoretical breakthroughs in the spatiotemporal big data research.展开更多
Artificial Intelligence (AI) is transforming organizational dynamics, and revolutionizing corporate leadership practices. This research paper delves into the question of how AI influences corporate leadership, examini...Artificial Intelligence (AI) is transforming organizational dynamics, and revolutionizing corporate leadership practices. This research paper delves into the question of how AI influences corporate leadership, examining both its advantages and disadvantages. Positive impacts of AI are evident in communication, feedback systems, tracking mechanisms, and decision-making processes within organizations. AI-powered communication tools, as exemplified by Slack, facilitate seamless collaboration, transcending geographical barriers. Feedback systems, like Adobe’s Performance Management System, employ AI algorithms to provide personalized development opportunities, enhancing employee growth. AI-based tracking systems optimize resource allocation, as exemplified by studies like “AI-Based Tracking Systems: Enhancing Efficiency and Accountability.” Additionally, AI-powered decision support, demonstrated during the COVID-19 pandemic, showcases the capability to navigate complex challenges and maintain resilience. However, AI adoption poses challenges in human resources, potentially leading to job displacement and necessitating upskilling efforts. Managing AI errors becomes crucial, as illustrated by instances like Amazon’s biased recruiting tool. Data privacy concerns also arise, emphasizing the need for robust security measures. The proposed solution suggests leveraging Local Machine Learning Models (LLMs) to address data privacy issues. Approaches such as federated learning, on-device learning, differential privacy, and homomorphic encryption offer promising strategies. By exploring the evolving dynamics of AI and leadership, this research advocates for responsible AI adoption and proposes LLMs as a potential solution, fostering a balanced integration of AI benefits while mitigating associated risks in corporate settings.展开更多
In order to take full advantage of federated filter in fault-tolerant design of integrated navigation system, the limitation of fault detection algorithm for gradual changing fault detection and the poor fault toleran...In order to take full advantage of federated filter in fault-tolerant design of integrated navigation system, the limitation of fault detection algorithm for gradual changing fault detection and the poor fault tolerance of global optimal fusion algorithm are the key problems to deal with. Based on theoretical analysis of the influencing factors of federated filtering fault tolerance, global fault-tolerant fusion algorithm and information sharing algorithm are proposed based on fuzzy assessment. It achieves intelligent fault-tolerant structure with two-stage and feedback, including real-time fault detection in sub-filters, and fault-tolerant fusion and information sharing in main filter. The simulation results demonstrate that the algorithm can effectively improve fault-tolerant ability and ensure relatively high positioning precision of integrated navigation system when a subsystem having gradual changing fault.展开更多
In order to improve the autonomous navigation capability of satellite,a pulsar/CNS（celestial navigation system） integrated navigation method based on federated unscented Kalman filter（UKF） is proposed.The celestia...In order to improve the autonomous navigation capability of satellite,a pulsar/CNS（celestial navigation system） integrated navigation method based on federated unscented Kalman filter（UKF） is proposed.The celestial navigation is a mature and stable navigation method.However,its position determination performance is not satisfied due to the low accuracy of horizon sensor.Single pulsar navigation is a new navigation method,which can provide highly accurate range measurements.The major drawback of single pulsar navigation is that the system is completely unobservable.As two methods are complementary to each other,the federated UKF is used here for fusing the navigation data from single pulsar navigation and CNS.Compared to the traditional celestial navigation method and single pulsar navigation,the integrated navigation method can provide better navigation performance.The simulation results demonstrate the feasibility and effectiveness of the navigation method.展开更多
In this study, a blockchain based federated learning system using an enhanced weighted mean vector optimization algorithm, known as EINFO, is proposed. The proposed EINFO addresses the limitations of federated averagi...In this study, a blockchain based federated learning system using an enhanced weighted mean vector optimization algorithm, known as EINFO, is proposed. The proposed EINFO addresses the limitations of federated averaging during global update and model training, where data is unevenly distributed among devices and there are variations in the number of data samples. Using a well-defined structure and updating the vector positions by local searching, vector combining, and updating rules, the EINFO algorithm maximizes the shared model parameters. In order to increase the exploration and exploitation capabilities, the model convergence rate is improved and new vectors are generated through the use of a weighted mean vector based on the inverse square law. To choose validators, miners, and to propagate new blocks, a delegated proof of stake based on the reliability of blockchain nodes is suggested. Federated learning is included into the blockchain to protect nodes from both external and internal threats. To determine how well the suggested system performs in relation to current models in the literature, extensive simulations are run. The simulation results show that the proposed system outperforms existing schemes in terms of accuracy, sensitivity and specificity.展开更多
The federated self-supervised framework is a distributed machine learning method that combines federated learning and self-supervised learning, which can effectively solve the problem of traditional federated learning...The federated self-supervised framework is a distributed machine learning method that combines federated learning and self-supervised learning, which can effectively solve the problem of traditional federated learning being difficult to process large-scale unlabeled data. The existing federated self-supervision framework has problems with low communication efficiency and high communication delay between clients and central servers. Therefore, we added edge servers to the federated self-supervision framework to reduce the pressure on the central server caused by frequent communication between both ends. A communication compression scheme using gradient quantization and sparsification was proposed to optimize the communication of the entire framework, and the algorithm of the sparse communication compression module was improved. Experiments have proved that the learning rate changes of the improved sparse communication compression module are smoother and more stable. Our communication compression scheme effectively reduced the overall communication overhead.展开更多
The influence of non-Independent Identically Distribution(non-IID)data on Federated Learning(FL)has been a serious concern.Clustered Federated Learning(CFL)is an emerging approach for reducing the impact of non-IID da...The influence of non-Independent Identically Distribution(non-IID)data on Federated Learning(FL)has been a serious concern.Clustered Federated Learning(CFL)is an emerging approach for reducing the impact of non-IID data,which employs the client similarity calculated by relevant metrics for clustering.Unfortunately,the existing CFL methods only pursue a single accuracy improvement,but ignore the convergence rate.Additionlly,the designed client selection strategy will affect the clustering results.Finally,traditional semi-supervised learning changes the distribution of data on clients,resulting in higher local costs and undesirable performance.In this paper,we propose a novel CFL method named ASCFL,which selects clients to participate in training and can dynamically adjust the balance between accuracy and convergence speed with datasets consisting of labeled and unlabeled data.To deal with unlabeled data,the prediction labels strategy predicts labels by encoders.The client selection strategy is to improve accuracy and reduce overhead by selecting clients with higher losses participating in the current round.What is more,the similarity-based clustering strategy uses a new indicator to measure the similarity between clients.Experimental results show that ASCFL has certain advantages in model accuracy and convergence speed over the three state-of-the-art methods with two popular datasets.展开更多
In the context of edge computing environments in general and the metaverse in particular,federated learning(FL)has emerged as a distributed machine learning paradigm that allows multiple users to collaborate on traini...In the context of edge computing environments in general and the metaverse in particular,federated learning(FL)has emerged as a distributed machine learning paradigm that allows multiple users to collaborate on training a shared machine learning model locally,eliminating the need for uploading raw data to a central server.It is perhaps the only training paradigm that preserves the privacy of user data,which is essential for computing environments as personal as the metaverse.However,the original FL architecture proposed is not scalable to a large number of user devices in the metaverse community.To mitigate this problem,hierarchical federated learning(HFL)has been introduced as a general distributed learning paradigm,inspiring a number of research works.In this paper,we present several types of HFL architectures,with a special focus on the three-layer client-edge-cloud HFL architecture,which is most pertinent to the metaverse due to its delay-sensitive nature.We also examine works that take advantage of the natural layered organization of three-layer client-edge-cloud HFL to tackle some of the most challenging problems in FL within the metaverse.Finally,we outline some future research directions of HFL in the metaverse.展开更多
This paper studies a federated edge learning system,in which an edge server coordinates a set of edge devices to train a shared machine learning(ML)model based on their locally distributed data samples.During the dist...This paper studies a federated edge learning system,in which an edge server coordinates a set of edge devices to train a shared machine learning(ML)model based on their locally distributed data samples.During the distributed training,we exploit the joint communication and computation design for improving the system energy efficiency,in which both the communication resource allocation for global ML-parameters aggregation and the computation resource allocation for locally updating ML-parameters are jointly optimized.In particular,we consider two transmission protocols for edge devices to upload ML-parameters to edge server,based on the non-orthogonal multiple access(NOMA)and time division multiple access(TDMA),respectively.Under both protocols,we minimize the total energy consumption at all edge devices over a particular finite training duration subject to a given training accuracy,by jointly optimizing the transmission power and rates at edge devices for uploading ML-parameters and their central processing unit(CPU)frequencies for local update.We propose efficient algorithms to solve the formulated energy minimization problems by using the techniques from convex optimization.Numerical results show that as compared to other benchmark schemes,our proposed joint communication and computation design significantly can improve the energy efficiency of the federated edge learning system,by properly balancing the energy tradeoff between communication and computation.展开更多
This paper presents a data fusion method in distributed multi-sensor system including GPS and INS sensors’ data processing. First, a residual χ 2 \|test strategy with the corresponding algorithm is designed. Then a ...This paper presents a data fusion method in distributed multi-sensor system including GPS and INS sensors’ data processing. First, a residual χ 2 \|test strategy with the corresponding algorithm is designed. Then a coefficient matrices calculation method of the information sharing principle is derived. Finally, the federated Kalman filter is used to combine these independent, parallel, real\|time data. A pseudolite (PL) simulation example is given.展开更多
Standard machine-learning approaches involve the centralization of training data in a data center,where centralized machine-learning algorithms can be applied for data analysis and inference.However,due to privacy res...Standard machine-learning approaches involve the centralization of training data in a data center,where centralized machine-learning algorithms can be applied for data analysis and inference.However,due to privacy restrictions and limited communication resources in wireless networks,it is often undesirable or impractical for the devices to transmit data to parameter sever.One approach to mitigate these problems is federated learning(FL),which enables the devices to train a common machine learning model without data sharing and transmission.This paper provides a comprehensive overview of FL applications for envisioned sixth generation(6G)wireless networks.In particular,the essential requirements for applying FL to wireless communications are first described.Then potential FL applications in wireless communications are detailed.The main problems and challenges associated with such applications are discussed.Finally,a comprehensive FL implementation for wireless communications is described.展开更多
Federated learning is a distributed machine learning technique that trains a global model by exchanging model parameters or intermediate results among multiple data sources. Although federated learning achieves physic...Federated learning is a distributed machine learning technique that trains a global model by exchanging model parameters or intermediate results among multiple data sources. Although federated learning achieves physical isolation of data, the local data of federated learning clients are still at risk of leakage under the attack of malicious individuals. For this reason, combining data protection techniques (e.g., differential privacy techniques) with federated learning is a sure way to further improve the data security of federated learning models. In this survey, we review recent advances in the research of differentially-private federated learning models. First, we introduce the workflow of federated learning and the theoretical basis of differential privacy. Then, we review three differentially-private federated learning paradigms: central differential privacy, local differential privacy, and distributed differential privacy. After this, we review the algorithmic optimization and communication cost optimization of federated learning models with differential privacy. Finally, we review the applications of federated learning models with differential privacy in various domains. By systematically summarizing the existing research, we propose future research opportunities.展开更多
Benefiting from the development of Federated Learning(FL)and distributed communication systems,large-scale intelligent applications become possible.Distributed devices not only provide adequate training data,but also ...Benefiting from the development of Federated Learning(FL)and distributed communication systems,large-scale intelligent applications become possible.Distributed devices not only provide adequate training data,but also cause privacy leakage and energy consumption.How to optimize the energy consumption in distributed communication systems,while ensuring the privacy of users and model accuracy,has become an urgent challenge.In this paper,we define the FL as a 3-layer architecture including users,agents and server.In order to find a balance among model training accuracy,privacy-preserving effect,and energy consumption,we design the training process of FL as game models.We use an extensive game tree to analyze the key elements that influence the players’decisions in the single game,and then find the incentive mechanism that meet the social norms through the repeated game.The experimental results show that the Nash equilibrium we obtained satisfies the laws of reality,and the proposed incentive mechanism can also promote users to submit high-quality data in FL.Following the multiple rounds of play,the incentive mechanism can help all players find the optimal strategies for energy,privacy,and accuracy of FL in distributed communication systems.展开更多
Federated learning came into being with the increasing concern of privacy security,as people’s sensitive information is being exposed under the era of big data.It is an algorithm that does not collect users’raw data...Federated learning came into being with the increasing concern of privacy security,as people’s sensitive information is being exposed under the era of big data.It is an algorithm that does not collect users’raw data,but aggregates model parameters from each client and therefore protects user’s privacy.Nonetheless,due to the inherent distributed nature of federated learning,it is more vulnerable under attacks since users may upload malicious data to break down the federated learning server.In addition,some recent studies have shown that attackers can recover information merely from parameters.Hence,there is still lots of room to improve the current federated learning frameworks.In this survey,we give a brief review of the state-of-the-art federated learning techniques and detailedly discuss the improvement of federated learning.Several open issues and existing solutions in federated learning are discussed.We also point out the future research directions of federated learning.展开更多
基金supported by the National Natural Science Foundation of China (60535010)
文摘A new nonlinear algorithm is proposed for strapdown inertial navigation system （SINS）/celestial navigation system （CNS）/global positioning system （GPS） integrated navigation systems. The algorithm employs a nonlinear system error model which can be modified by unscented Kalman filter （UKF） to give predictions of local filters. And these predictions can be fused by the federated Kalman filter. In the system error model, the rotation vector is introduced to denote vehicle＇s attitude and has less variables than the quaternion. Also, the UKF method is simplified to estimate the system error model, which can both lead to less calculation and reduce algorithm implement time. In the information fusion section, a modified federated Kalman filter is proposed to solve the singular covariance problem. Specifically, the new algorithm is applied to maneuvering vehicles, and simulation results show that this algorithm is more accurate than the linear integrated navigation algorithm.
基金supported by the National Research Foundation(NRF),Singapore,under Singapore Energy Market Authority(EMA),Energy Resilience,NRF2017EWT-EP003-041,Singapore NRF2015NRF-ISF001-2277Singapore NRF National Satellite of Excellence,Design Science and Technology for Secure Critical Infrastructure NSoE DeST-SCI2019-0007+4 种基金A*STARNTU-SUTD Joint Research Grant on Artificial Intelligence for the Future of Manufacturing RGANS1906,Wallenberg AI,Autonomous Systems and Software Program and Nanyang Technological University(WASP/NTU)under grant M4082187(4080),and NTU-We Bank JRI(NWJ-2020-004)Alibaba Group through Alibaba Innovative Research(AIR)Program and Alibaba-NTU Singapore Joint Research Institute(JRI),NTU,SingaporeNational Key Research and Development Program of China under Grant 2018YFC0809803 and Grant 2019YFB2101901Young Innovation Talents Project in Higher Education of Guangdong Province,China under grant No.2018KQNCX333in part by the National Science Foundation of China under Grant 61702364。
文摘As the 5G communication networks are being widely deployed worldwide,both industry and academia have started to move beyond 5G and explore 6G communications.It is generally believed that 6G will be established on ubiquitous Artificial Intelligence(AI)to achieve data-driven Machine Learning(ML)solutions in heterogeneous and massive-scale networks.However,traditional ML techniques require centralized data collection and processing by a central server,which is becoming a bottleneck of large-scale implementation in daily life due to significantly increasing privacy concerns.Federated learning,as an emerging distributed AI approach with privacy preservation nature,is particularly attractive for various wireless applications,especially being treated as one of the vital solutions to achieve ubiquitous AI in 6G.In this article,we first introduce the integration of 6G and federated learning and provide potential federated learning applications for 6G.We then describe key technical challenges,the corresponding federated learning methods,and open problems for future research on federated learning in the context of 6G communications.
基金supported in part by the National Natural Science Foundation of China(Basic Science Center Program:61988101)the Sino-German Center for Research Promotion(M-0066)+2 种基金the International(Regional)Cooperation and Exchange Project(61720106008)the Programme of Introducing Talents of Discipline to Universities(the 111 Project)(B17017)the Program of Shanghai Academic Research Leader(20XD1401300).
文摘Multi-agent systems can solve scientific issues related to complex systems that are difficult or impossible for a single agent to solve through mutual collaboration and cooperation optimization.In a multi-agent system,agents with a certain degree of autonomy generate complex interactions due to the correlation and coordination,which is manifested as cooperative/competitive behavior.This survey focuses on multi-agent cooperative optimization and cooperative/non-cooperative games.Starting from cooperative optimization,the studies on distributed optimization and federated optimization are summarized.The survey mainly focuses on distributed online optimization and its application in privacy protection,and overviews federated optimization from the perspective of privacy protection me-chanisms.Then,cooperative games and non-cooperative games are introduced to expand the cooperative optimization problems from two aspects of minimizing global costs and minimizing individual costs,respectively.Multi-agent cooperative and non-cooperative behaviors are modeled by games from both static and dynamic aspects,according to whether each player can make decisions based on the information of other players.Finally,future directions for cooperative optimization,cooperative/non-cooperative games,and their applications are discussed.
基金supported by the National Natural Science Foundation of China(Grant Nos.41421001,42050101,and 42050105)。
文摘Since the beginning of the 21 st century,the geoscience research has been entering a significant transitional period with the establishment of a new knowledge system as the core and with the drive of big data as the means.It is a revolutionary leap in the research of geoscience knowledge discovery from the traditional encyclopedic discipline knowledge system to the computer-understandable and operable knowledge graph.Based on adopting the graph pattern of general knowledge representation,the geoscience knowledge graph expands the unique spatiotemporal features to the Geoscience knowledge,and integrates geoscience knowledge elements,such as map,text,and number,to establish an all-domain geoscience knowledge representation model.A federated,crowd intelligence-based collaborative method of constructing the geoscience knowledge graph is developed here,which realizes the construction of high-quality professional knowledge graph in collaboration with global geo-scientists.We also develop a method for constructing a dynamic knowledge graph of multi-modal geoscience data based on in-depth text analysis,which extracts geoscience knowledge from massive geoscience literature to construct the latest and most complete dynamic geoscience knowledge graph.A comprehensive and systematic geoscience knowledge graph can not only deepen the existing geoscience big data analysis,but also advance the construction of the high-precision geological time scale driven by big data,the compilation of intelligent maps driven by rules and data,and the geoscience knowledge evolution and reasoning analysis,among others.It will further expand the new directions of geoscience research driven by both data and knowledge,break new ground where geoscience,information science,and data science converge,realize the original innovation of the geoscience research and achieve major theoretical breakthroughs in the spatiotemporal big data research.
文摘Artificial Intelligence (AI) is transforming organizational dynamics, and revolutionizing corporate leadership practices. This research paper delves into the question of how AI influences corporate leadership, examining both its advantages and disadvantages. Positive impacts of AI are evident in communication, feedback systems, tracking mechanisms, and decision-making processes within organizations. AI-powered communication tools, as exemplified by Slack, facilitate seamless collaboration, transcending geographical barriers. Feedback systems, like Adobe’s Performance Management System, employ AI algorithms to provide personalized development opportunities, enhancing employee growth. AI-based tracking systems optimize resource allocation, as exemplified by studies like “AI-Based Tracking Systems: Enhancing Efficiency and Accountability.” Additionally, AI-powered decision support, demonstrated during the COVID-19 pandemic, showcases the capability to navigate complex challenges and maintain resilience. However, AI adoption poses challenges in human resources, potentially leading to job displacement and necessitating upskilling efforts. Managing AI errors becomes crucial, as illustrated by instances like Amazon’s biased recruiting tool. Data privacy concerns also arise, emphasizing the need for robust security measures. The proposed solution suggests leveraging Local Machine Learning Models (LLMs) to address data privacy issues. Approaches such as federated learning, on-device learning, differential privacy, and homomorphic encryption offer promising strategies. By exploring the evolving dynamics of AI and leadership, this research advocates for responsible AI adoption and proposes LLMs as a potential solution, fostering a balanced integration of AI benefits while mitigating associated risks in corporate settings.
基金supported by the National Natural Science Foundationof China (60902055)
文摘In order to take full advantage of federated filter in fault-tolerant design of integrated navigation system, the limitation of fault detection algorithm for gradual changing fault detection and the poor fault tolerance of global optimal fusion algorithm are the key problems to deal with. Based on theoretical analysis of the influencing factors of federated filtering fault tolerance, global fault-tolerant fusion algorithm and information sharing algorithm are proposed based on fuzzy assessment. It achieves intelligent fault-tolerant structure with two-stage and feedback, including real-time fault detection in sub-filters, and fault-tolerant fusion and information sharing in main filter. The simulation results demonstrate that the algorithm can effectively improve fault-tolerant ability and ensure relatively high positioning precision of integrated navigation system when a subsystem having gradual changing fault.
基金supported by the National High Technology Research and Development Program of China(2006AAJ109)Aviation Science Fund(20070818001)
文摘In order to improve the autonomous navigation capability of satellite,a pulsar/CNS（celestial navigation system） integrated navigation method based on federated unscented Kalman filter（UKF） is proposed.The celestial navigation is a mature and stable navigation method.However,its position determination performance is not satisfied due to the low accuracy of horizon sensor.Single pulsar navigation is a new navigation method,which can provide highly accurate range measurements.The major drawback of single pulsar navigation is that the system is completely unobservable.As two methods are complementary to each other,the federated UKF is used here for fusing the navigation data from single pulsar navigation and CNS.Compared to the traditional celestial navigation method and single pulsar navigation,the integrated navigation method can provide better navigation performance.The simulation results demonstrate the feasibility and effectiveness of the navigation method.
文摘In this study, a blockchain based federated learning system using an enhanced weighted mean vector optimization algorithm, known as EINFO, is proposed. The proposed EINFO addresses the limitations of federated averaging during global update and model training, where data is unevenly distributed among devices and there are variations in the number of data samples. Using a well-defined structure and updating the vector positions by local searching, vector combining, and updating rules, the EINFO algorithm maximizes the shared model parameters. In order to increase the exploration and exploitation capabilities, the model convergence rate is improved and new vectors are generated through the use of a weighted mean vector based on the inverse square law. To choose validators, miners, and to propagate new blocks, a delegated proof of stake based on the reliability of blockchain nodes is suggested. Federated learning is included into the blockchain to protect nodes from both external and internal threats. To determine how well the suggested system performs in relation to current models in the literature, extensive simulations are run. The simulation results show that the proposed system outperforms existing schemes in terms of accuracy, sensitivity and specificity.
文摘The federated self-supervised framework is a distributed machine learning method that combines federated learning and self-supervised learning, which can effectively solve the problem of traditional federated learning being difficult to process large-scale unlabeled data. The existing federated self-supervision framework has problems with low communication efficiency and high communication delay between clients and central servers. Therefore, we added edge servers to the federated self-supervision framework to reduce the pressure on the central server caused by frequent communication between both ends. A communication compression scheme using gradient quantization and sparsification was proposed to optimize the communication of the entire framework, and the algorithm of the sparse communication compression module was improved. Experiments have proved that the learning rate changes of the improved sparse communication compression module are smoother and more stable. Our communication compression scheme effectively reduced the overall communication overhead.
基金supported by the National Key Research and Development Program of China(No.2019YFC1520904)the National Natural Science Foundation of China(No.61973250).
文摘The influence of non-Independent Identically Distribution(non-IID)data on Federated Learning(FL)has been a serious concern.Clustered Federated Learning(CFL)is an emerging approach for reducing the impact of non-IID data,which employs the client similarity calculated by relevant metrics for clustering.Unfortunately,the existing CFL methods only pursue a single accuracy improvement,but ignore the convergence rate.Additionlly,the designed client selection strategy will affect the clustering results.Finally,traditional semi-supervised learning changes the distribution of data on clients,resulting in higher local costs and undesirable performance.In this paper,we propose a novel CFL method named ASCFL,which selects clients to participate in training and can dynamically adjust the balance between accuracy and convergence speed with datasets consisting of labeled and unlabeled data.To deal with unlabeled data,the prediction labels strategy predicts labels by encoders.The client selection strategy is to improve accuracy and reduce overhead by selecting clients with higher losses participating in the current round.What is more,the similarity-based clustering strategy uses a new indicator to measure the similarity between clients.Experimental results show that ASCFL has certain advantages in model accuracy and convergence speed over the three state-of-the-art methods with two popular datasets.
文摘In the context of edge computing environments in general and the metaverse in particular,federated learning(FL)has emerged as a distributed machine learning paradigm that allows multiple users to collaborate on training a shared machine learning model locally,eliminating the need for uploading raw data to a central server.It is perhaps the only training paradigm that preserves the privacy of user data,which is essential for computing environments as personal as the metaverse.However,the original FL architecture proposed is not scalable to a large number of user devices in the metaverse community.To mitigate this problem,hierarchical federated learning(HFL)has been introduced as a general distributed learning paradigm,inspiring a number of research works.In this paper,we present several types of HFL architectures,with a special focus on the three-layer client-edge-cloud HFL architecture,which is most pertinent to the metaverse due to its delay-sensitive nature.We also examine works that take advantage of the natural layered organization of three-layer client-edge-cloud HFL to tackle some of the most challenging problems in FL within the metaverse.Finally,we outline some future research directions of HFL in the metaverse.
基金the National Key R&D Program of China under Grant 2018YFB1800800Guangdong Province Key Area R&D Program under Grant 2018B030338001the Natural Science Foundation of China under Grant U2001208。
文摘This paper studies a federated edge learning system,in which an edge server coordinates a set of edge devices to train a shared machine learning(ML)model based on their locally distributed data samples.During the distributed training,we exploit the joint communication and computation design for improving the system energy efficiency,in which both the communication resource allocation for global ML-parameters aggregation and the computation resource allocation for locally updating ML-parameters are jointly optimized.In particular,we consider two transmission protocols for edge devices to upload ML-parameters to edge server,based on the non-orthogonal multiple access(NOMA)and time division multiple access(TDMA),respectively.Under both protocols,we minimize the total energy consumption at all edge devices over a particular finite training duration subject to a given training accuracy,by jointly optimizing the transmission power and rates at edge devices for uploading ML-parameters and their central processing unit(CPU)frequencies for local update.We propose efficient algorithms to solve the formulated energy minimization problems by using the techniques from convex optimization.Numerical results show that as compared to other benchmark schemes,our proposed joint communication and computation design significantly can improve the energy efficiency of the federated edge learning system,by properly balancing the energy tradeoff between communication and computation.
文摘This paper presents a data fusion method in distributed multi-sensor system including GPS and INS sensors’ data processing. First, a residual χ 2 \|test strategy with the corresponding algorithm is designed. Then a coefficient matrices calculation method of the information sharing principle is derived. Finally, the federated Kalman filter is used to combine these independent, parallel, real\|time data. A pseudolite (PL) simulation example is given.
基金This work was supported by research grants from the Engineering and Physical Sciences Research Council(EPSRC),UK(EP/T015985/1)from US National Science Foundation(CCF-1908308).
文摘Standard machine-learning approaches involve the centralization of training data in a data center,where centralized machine-learning algorithms can be applied for data analysis and inference.However,due to privacy restrictions and limited communication resources in wireless networks,it is often undesirable or impractical for the devices to transmit data to parameter sever.One approach to mitigate these problems is federated learning(FL),which enables the devices to train a common machine learning model without data sharing and transmission.This paper provides a comprehensive overview of FL applications for envisioned sixth generation(6G)wireless networks.In particular,the essential requirements for applying FL to wireless communications are first described.Then potential FL applications in wireless communications are detailed.The main problems and challenges associated with such applications are discussed.Finally,a comprehensive FL implementation for wireless communications is described.
文摘Federated learning is a distributed machine learning technique that trains a global model by exchanging model parameters or intermediate results among multiple data sources. Although federated learning achieves physical isolation of data, the local data of federated learning clients are still at risk of leakage under the attack of malicious individuals. For this reason, combining data protection techniques (e.g., differential privacy techniques) with federated learning is a sure way to further improve the data security of federated learning models. In this survey, we review recent advances in the research of differentially-private federated learning models. First, we introduce the workflow of federated learning and the theoretical basis of differential privacy. Then, we review three differentially-private federated learning paradigms: central differential privacy, local differential privacy, and distributed differential privacy. After this, we review the algorithmic optimization and communication cost optimization of federated learning models with differential privacy. Finally, we review the applications of federated learning models with differential privacy in various domains. By systematically summarizing the existing research, we propose future research opportunities.
基金sponsored by the National Key R&D Program of China(No.2018YFB2100400)the National Natural Science Foundation of China(No.62002077,61872100)+4 种基金the Major Research Plan of the National Natural Science Foundation of China(92167203)the Guangdong Basic and Applied Basic Research Foundation(No.2020A1515110385)the China Postdoctoral Science Foundation(No.2022M710860)the Zhejiang Lab(No.2020NF0AB01)Guangzhou Science and Technology Plan Project(202102010440).
文摘Benefiting from the development of Federated Learning(FL)and distributed communication systems,large-scale intelligent applications become possible.Distributed devices not only provide adequate training data,but also cause privacy leakage and energy consumption.How to optimize the energy consumption in distributed communication systems,while ensuring the privacy of users and model accuracy,has become an urgent challenge.In this paper,we define the FL as a 3-layer architecture including users,agents and server.In order to find a balance among model training accuracy,privacy-preserving effect,and energy consumption,we design the training process of FL as game models.We use an extensive game tree to analyze the key elements that influence the players’decisions in the single game,and then find the incentive mechanism that meet the social norms through the repeated game.The experimental results show that the Nash equilibrium we obtained satisfies the laws of reality,and the proposed incentive mechanism can also promote users to submit high-quality data in FL.Following the multiple rounds of play,the incentive mechanism can help all players find the optimal strategies for energy,privacy,and accuracy of FL in distributed communication systems.
基金This work was supported by Guangdong Provincial Key Laboratory(2020B121201001).
文摘Federated learning came into being with the increasing concern of privacy security,as people’s sensitive information is being exposed under the era of big data.It is an algorithm that does not collect users’raw data,but aggregates model parameters from each client and therefore protects user’s privacy.Nonetheless,due to the inherent distributed nature of federated learning,it is more vulnerable under attacks since users may upload malicious data to break down the federated learning server.In addition,some recent studies have shown that attackers can recover information merely from parameters.Hence,there is still lots of room to improve the current federated learning frameworks.In this survey,we give a brief review of the state-of-the-art federated learning techniques and detailedly discuss the improvement of federated learning.Several open issues and existing solutions in federated learning are discussed.We also point out the future research directions of federated learning.
