检索结果-内蒙古大学图书馆

Towards Fair and Scalable Trial Assignment in Federated Bandits: A Shapley Value Approach

IEEE Transactions on Big Data 2024年 1-14页

作者： Wang, Zibo Zhu, Yifei Wang, Dan Han, Zhu UM-SJTU Joint Institute Shanghai Jiao Tong University Shanghai China UM-SJTU Joint Institute and Cooperative Medianet Innovation Center Shanghai Jiao Tong University Shanghai China Department of Computing The Hong Kong Polytechnic University Hong Kong China Department of Electrical and Computer Engineering University of Houston Houston USA

Federated multi-armed bandits extend the multi-armed bandits framework to the federated learning setting where multiple clients in the same exploration space collaboratively identify the optimal arm. While previous studies demonstrated its efficiency like classical federated learning, in this paper, we present the first work that reveals the serious fairness problem in federated multi-armed bandits when clients have heterogeneous and overlapping armsets. The fairness problem happens because clients with different trial requirements should conduct different numbers of trials summing up to a global requirement, but they wish to minimize their exploration effort. To address the novel fairness concern, we formally formulate the fairness-aware trial assignment as a coalitional game. Based on the theoretically derived trial requirements, we devise a Shapley value-based trial assignment mechanism to guarantee fairness. Regardless of the #P-hard complexity when deriving the general Shapley value, we achieve an accurate computation of trial assignment with polynomial complexity by exploiting its unique characteristic. We further carefully control the numbers of trials in each iteration to resolve the communication bottleneck and minimize the wasted trials. Experiment results show that, compared to the naïve federated scheme, our design outperforms with both high fairness metrics and high efficiency in total trials and communication. IEEE

关键词： Investments

来源：评论

学校读者我要写书评

暂无评论

Joint Optimization of Model Splitting and Device Task Assignment for Private Multi-hop Split Learning 59

Joint Optimization of Model Splitting and Device Task Assign...

引用

59th Annual Conference on Information Sciences and Systems, CISS 2025

作者： Wei, Dongyu Zhang, Qianqian Liu, Yuchen Chen, Mingzhe Rowan University Department of Electrical and Computer Engineering GlassboroNJ08028 United States Nc State University Department of Computer Science RaleighNC27695 United States University of Miami Department of Electrical and Computer Engineering Coral GablesFL33146 United States University of Miami Frost Institute for Data Science and Computing Coral GablesFL33146 United States

ISBN: (纸本)9798331513269

In this paper, a deceptive signal-assisted private split learning is investigated. In our model, several edge devices jointly perform collaborative training, and some eavesdroppers aim to collect the model and data information from devices. To prevent the eavesdropper from collecting model and data information, a subset of devices can transmit deceptive signals. Therefore, it is necessary to determine the subset of devices used for deceptive signal transmission, the subset of model training devices, and the models assigned to each model training device. This problem is formulated as an optimization problem whose goal is to minimize the eavesdropped information while meeting the model training energy consumption and delay constraints. To solve this problem, we propose an actor-critic deep reinforcement learning (AC-DRL) framework that enables a centralized agent to dynamically determine the model training devices, the deceptive signal transmission devices, the transmit power, and sub-models assigned to each model training device while considering network topology and device properties (e.g., energy and privacy constraints). The proposed AC-DRL framework integrates an actor network to generate optimal actions and a critic network to stabilize the learning process by evaluating the cumulative rewards. Simulation results demonstrate that the proposed method improves the convergence rate by 3× and the accumulated reward by up to 40% compared with the proximal policy optimization (PPO) algorithm. © 2025 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Collaborative learning-based inter-dependent task dispatching and co-location in an integrated edge computing system

引用

Digital Communications and Networks 2024年第6期10卷 1837-1850页

作者： Uchechukwu Awada Jiankang Zhang Sheng Chen Shuangzhi Li Shouyi Yang School of Software Henan Institute of Science and TechnologyXinxiang 453003China School of Electrical and Information Engineering Zhengzhou UniversityZhengzhou 450001China Department of Computing and Informatics Bournemouth UniversityPoole BH125BBUK School of Electronics and Computer Science University of SouthamptonSouthampton SO171BJUK Faculty of Information Science and Engineering Ocean University of ChinaQingdao 266100China

Recently,several edge deployment types,such as on-premise edge clusters,Unmanned Aerial Vehicles(UAV)-attached edge devices,telecommunication base stations installed with edge clusters,etc.,are being deployed to enable faster response time for latency-sensitive *** fundamental problem is where and how to offload and schedule multi-dependent tasks so as to minimize their collective execution time and to achieve high resource *** approaches randomly dispatch tasks naively to available edge nodes without considering the resource demands of tasks,inter-dependencies of tasks and edge resource *** approaches can result in the longer waiting time for tasks due to insufficient resource availability or dependency support,as well as provider ***,we present Edge Colla,which is based on the integration of edge resources running across multi-edge *** Colla leverages learning techniques to intelligently dispatch multidependent tasks,and a variant bin-packing optimization method to co-locate these tasks firmly on available nodes to optimally utilize *** experiments on real-world datasets from Alibaba on task dependencies show that our approach can achieve optimal performance than the baseline schemes.

关键词： Edge computing Collaborative learning Resource utilization Execution time Edge federation Gang scheduling

来源：评论

学校读者我要写书评

暂无评论

Federated Model Heterogeneous Matryoshka Representation Learning 38

Federated Model Heterogeneous Matryoshka Representation Lear...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Yi, Liping Yu, Han Ren, Chao Wang, Gang Liu, Xiaoguang Li, Xiaoxiao College of Computer Science TMCC SysNet DISSec GTIISC Nankai University China College of Computing and Data Science Nanyang Technological University Singapore Department of Electrical and Computer Engineering The University of British Columbia Canada Vector Institute Canada

Model heterogeneous federated learning (MHeteroFL) enables FL clients to collaboratively train models with heterogeneous structures in a distributed fashion. However, existing MHeteroFL methods rely on training loss to transfer knowledge between the client model and the server model, resulting in limited knowledge exchange. To address this limitation, we propose the Federated model heterogeneous Matryoshka Representation Learning (FedMRL) approach for supervised learning tasks. It adds an auxiliary small homogeneous model shared by clients with heterogeneous local models. (1) The generalized and personalized representations extracted by the two models' feature extractors are fused by a personalized lightweight representation projector. This step enables representation fusion to adapt to local data distribution. (2) The fused representation is then used to construct Matryoshka representations with multi-dimensional and multi-granular embedded representations learned by the global homogeneous model header and the local heterogeneous model header. This step facilitates multi-perspective representation learning and improves model learning capability. Theoretical analysis shows that FedMRL achieves a O(1/T) non-convex convergence rate. Extensive experiments on benchmark datasets demonstrate its superior model accuracy with low communication and computational costs compared to seven state-of-the-art baselines. It achieves up to 8.48% and 24.94% accuracy improvement compared with the state-of-the-art and the best same-category baseline, respectively. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

quantum Network Utility Maximization 4

Quantum Network Utility Maximization

引用

4th IEEE International Conference on quantum computing and engineering, QCE 2023

作者： Vardoyan, Gayane Wehner, Stephanie Delft University of Technology QuTech Netherlands Quantum Computer Science Electrical Engineering Mathematics and Computer Science Delft University of Technology Netherlands Kavli Institute of Nanoscience Delft University of Technology Netherlands

ISBN: (纸本)9798350343236

Network Utility Maximization (NUM) is a mathe-matical framework that has endowed researchers with powerful methods for designing and analyzing classical communication protocols. NUM has also enabled the development of distributed algorithms for solving the resource allocation problem, while at the same time providing certain guarantees, e.g., that of fair treatment, to the users of a network. We extend here the notion of NUM to quantum networks, and propose three quantum utility functions - each incorporating a different entanglement measure. We aim both to gain an understanding of some of the ways in which quantum users may perceive utility, as well as to explore structured and theoretically-motivated methods of simultaneously servicing multiple users in distributed quantum systems. Using our quantum NUM constructions, we develop an optimization framework for networks that use the single-photon scheme for entanglement generation, which enables us to solve the resource allocation problem while exploring rate-fidelity tradeoffs within the network topologies that we consider. We learn that two of our utility functions, which are based on distillable entanglement and secret key fraction, are in close agreement with each other and produce similar solutions to the optimization problems we study. While these two utilities place a higher emphasis on end-to-end fidelity, our third utility- based on entanglement negativity - has more favorable mathematical properties, and tends to place a higher value on the rate at which users receive entangled resources. These contrasting behaviors thus provide ideas regarding the suitability of quantum network utility definitions to different quantum applications. © 2023 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Mitigating Scattering in a quantum System Using Only an Integrating Sphere

引用

PRX quantum 2024年第3期5卷 030351页

作者： Zhenfei Jiang Tian Li Matthew L. Boone Zhenhuan Yi Alexei V. Sokolov Girish S. Agarwal Marlan O. Scully Institute for Quantum Science and Engineering Department of Physics and Astronomy Department of Chemistry and Physics UTC Research Institute Department of Physics Department of Biological and Agricultural Engineering Department of Electrical and Computer Engineering

Strong quantum correlated sources are essential but delicate resources for quantum information science and engineering protocols. Decoherence and loss are the two main disruptive processes that lead to the loss of nonclassical behavior in quantum correlations. In quantum systems, scattering can contribute to both decoherence and loss. In this work, we present an experimental scheme capable of significantly mitigating the adverse impact of scattering in quantum systems. Our quantum system is composed of a two-mode squeezed light generated with the four-wave-mixing process in hot rubidium vapor and a scatterer is introduced to one of the two modes. An integrating sphere is then placed after the scatterer to recollect the scattered photons. We use mutual information between the two modes as the measure of quantum correlations and demonstrate a 47.5% mutual information recovery from scattering, despite an enormous photon loss of greater than 85%. Our scheme is the very first step toward recovering quantum correlations from disruptive random processes and thus has the potential to bridge the gap between proof-of-principle demonstrations and practical real-world implementations of quantum protocols.

关键词： Open quantum systems & decoherence quantum correlations in quantum information quantum correlations, foundations & formalism

来源：评论

学校读者我要写书评

暂无评论

Foundry-fabricated photonic integrated circuit for flex-grid entanglement distribution

Foundry-fabricated photonic integrated circuit for flex-grid...

引用

CLEO: Science and Innovations in CLEO 2024, CLEO: S and I 2024 - Part of Conference on Lasers and Electro-Optics

作者： Miloshevsky, Alexander Lu, Hsuan-Hao Cohen, Lucas M. Myilswamy, Karthik V. Fatema, Saleha Alshowkan, Muneer Weiner, Andrew M. Lukens, Joseph M. Quantum Information Science Section Computational Sciences and Engineering Division Oak Ridge National Laboratory Oak RidgeTN37831 United States School of Electrical and Computer Engineering Purdue Quantum Science and Engineering Institute Purdue University West LafayetteIN47907 United States Research Technology Office and Quantum Collaborative Arizona State University TempeAZ85287 United States

We demonstrate a silicon photonic integrated circuit fabricated through the CMOS manufacturing process, which features a bidirectionally pumped microring to achieve over 116 high-fidelity polarization entangled channe... 详细信息

关键词： Photonic integrated circuits

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Lifespan Prediction Modelling for Electric Submersible Pumps in Oil Wells 2

Machine Learning-Based Lifespan Prediction Modelling for Ele...

引用

2nd International Conference Computational and Characterization Techniques in engineering and Sciences, IC3TES 2024

作者： Rajakala, J. Gupta, Satyaveer Naidu, Pothala Mutyalu Basi Reddy, A. Revathi, S. Selvan, R. Senthamil Sai Spurthi Institute of Technology Department of Computer Science and Engineering Gangaram India Delhi Technical Campus Department of Electrical Engineering Greater Noida India Vignan Institute of Technology And Science Department of Cse Hyderabad India Mohan Babu University School of Computing Department of Computer Science and Engineering Tirupati India Sri Ramakrishna Institute of Technology Department of Computer Science and Engineering Coimbatore India Annamacharya Institute of Technology and Sciences Department of Electronics and Communication Engineering Tirupati India

ISBN: (纸本)9798350364699

To maintain the output flow rate and prolong the life of oil wells, artificial lift is crucial to the petroleum industry. Electric Submersible Pumps (ESP) are a widely used artificial lift technique due to their ability to generate large flow rates in very deep wells. ESPs have a much shorter lifetime than anticipated, even though they are designed to function in harsh environments including corrosion, high temperatures, and high pressure. Because ESP intervention work is far more expensive than other artificial lift techniques, particularly for offshore wells, ESP failures result in production loss and raise replacement costs. Knowing when an ESP may fail is thus highly helpful in the oil production industry and affects how oil wells are designed, built, and managed. Using three machine learning algorithms - Decision Tree, Random Forest, and Gradient Boosting Machine - this study contributes to the construction of prediction models for ESP lifespan that take into account both dynamic and static ESP features. The model that produced the best results for ESP life cycle prediction was determined by comparing the output of various models. To predict the most influential characteristics on the length of ESP, this research also assessed the influence factor of different operational parameters. By knowing more about ESP behavior, early efforts to avert possible ESP failures may be realized thanks to the study's findings. © 2024 IEEE.

关键词： Submersible pumps

来源：评论

学校读者我要写书评

暂无评论

Joint Communication and Synchronization Performance Optimization in Digital Twin Enabled Networks

Joint Communication and Synchronization Performance Optimiza...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Yu, Hanzhi Liu, Yuchen Chen, Mingzhe University of Miami Department of Electrical and Computer Engineering Frost Institute for Data Science and Computing Coral GablesFL33146 United States North Carolina State University Department of Computer Science RaleighNC27695 United States

ISBN: (纸本)9798350351255

In this paper, we investigate an accurate synchronization between a physical network and its digital network twin (DNT) that is a virtual representation of the physical network. The considered network includes a physical network where a base station (BS) serves a set of users, and a DNT that evolves with the status of both DNT and the physical network. The BS must use its limited spectrum resources to serve the users, as well as transmit the physical network information to the cloud server for DNT synchronization. Since the DNT can predict the physical network status, the BS may not need to transmit physical network information to the server at each time slot thus saving spectrum resources to serve users. However, if the BS does not transmit physical information to the DNT over a long period of time, the DNT may not be able to represent the physical network accurately. To this end, the BS must determine whether to send physical network information to the server to update DNT and the spectrum resources used for physical network information transmission and serving users. We formulate this resources allocation problem as an optimization problem aiming to maximize the sum of data rates of all users, while minimizing the gap between the states of the physical network and the DNT. The formulated problem is challenging to solve by conventional optimization methods, since the BS may not be able to know the future status of the DNT. To solve this problem, we design a gate recurrent unit (GRU) and soft action-critic (SAC) based algorithm. The GRU enables the DNT to predict its future states by using historical state data, and updating the DNT when the BS does not transmit physical network information. The SAC based algorithm enables the BS to learn the relationship between the physical network information transmission and the future status estimation accuracy of the DNT thus determining whether to transmit physical network information to the cloud server, ensuring an accurac

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Socialized Learning: A Survey of the Paradigm Shift for Edge Intelligence in Networked Systems

引用

IEEE Communications Surveys and Tutorials 2024年第3期27卷 2085-2128页

作者： Wang, Xiaofei Zhao, Yunfeng Qiu, Chao Hu, Qinghua Leung, Victor C. M. Tianjin University College of Intelligence and Computing Tianjin300072 China Shenzhen518000 China Shenzhen MSU-BIT University Artificial Intelligence Research Institute Shenzhen518172 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China The University of British Columbia Department of Electrical and Computer Engineering VancouverV6T 1Z4 Canada

Amidst the robust impetus from artificial intelligence (AI) and big data, edge intelligence (EI) has emerged as a nascent computing paradigm, synthesizing AI with edge computing (EC) to become an exemplary solution for unleashing the full potential of AI services. Nonetheless, challenges in communication costs, resource allocation, privacy, and security continue to constrain its proficiency in supporting services with diverse requirements. In response to these issues, this paper introduces socialized learning (SL) as a promising solution, further propelling the advancement of EI. SL is a learning paradigm predicated on social principles and behaviors, aimed at amplifying the collaborative capacity and collective intelligence of agents within the EI system. SL not only enhances the system's adaptability but also optimizes communication, and networking processes, essential for distributed intelligence across diverse devices and platforms. Therefore, a combination of SL and EI may greatly facilitate the development of collaborative intelligence in the future network. This paper presents the findings of a literature review on the integration of EI and SL, summarizing the latest achievements in existing research on EI and SL. Subsequently, we delve comprehensively into the limitations of EI and how it could benefit from SL. Special emphasis is placed on the communication challenges and networking strategies and other aspects within these systems, underlining the role of optimized network solutions in improving system efficiency. Based on these discussions, we elaborate in detail on three integrated components: socialized architecture, socialized training, and socialized inference, analyzing their strengths and weaknesses. Finally, we identify some possible future applications of combining SL and EI, discuss open problems and suggest some future research, with the hope of arousing the research community's interest in this emerging and exciting interdisciplinary field. © 1

关键词： Resource allocation

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：