CCSS: Collaborative Research: Towards a Resource Rationing Framework for Wireless Federated Learning

CCSS:协作研究:无线联邦学习的资源配给框架

基本信息

  • 批准号:
    2033681
  • 负责人:
  • 金额:
    $ 20万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Standard Grant
  • 财政年份:
    2020
  • 资助国家:
    美国
  • 起止时间:
    2020-09-01 至 2024-08-31
  • 项目状态:
    已结题

项目摘要

Federated learning (FL) is an emerging distributed machine learning paradigm that has many attractive properties. Despite the early studies that have demonstrated the potential of jointly optimizing communication and computation, existing designs are not tailored to the unique characteristics of FL. This project aims at developing a novel and rigorous resource allocation framework for wireless FL, which we term resource rationing to emphasize balancing resources over time so that the long-term impact to the final learning outcome is explicitly captured. Resource rationing is built on a rigorous theoretical foundation and guides the algorithmic development that solves specific resource allocation problems in both physical and Media Access Control (MAC) layers. Federated learning is an emerging new application for wireless communications, and this project has potential to advance the technology development of this new use case. Meanwhile, the theoretical foundation, algorithms, and validation will broadly advance the state of the art in machine learning, communication theory, and wireless networking. Developing such practical and impactful technology would also help maintain the leadership of the United States in wireless technologies as well as keep the pipeline to supply high-quality, well-trained, and innovative engineers.The project pursues synergistic activities for the successful design and implementation of resource rationing for wireless FL. Novel convergence analysis of FL with varying resource in each learning round is carried out, which establishes the general later-is-better principle. Guided by the theoretical foundation, the project further builds a comprehensive algorithmic framework for specific resource rationing designs, ranging from physical layer bit loading and adaptive coding and modulation to the MAC layer client selection, bandwidth allocation, and power control.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
联邦学习(FL)是一种新兴的分布式机器学习范式,具有许多吸引人的特性。尽管早期的研究已经证明了联合优化通信和计算的潜力,现有的设计是不适合FL的独特特性。该项目旨在开发一种新的和严格的无线FL的资源分配框架,我们长期的资源配给,强调随着时间的推移平衡资源,使最终的学习成果的长期影响被明确捕获。资源配给建立在严格的理论基础上,并指导解决物理和媒体访问控制(MAC)层中特定资源分配问题的算法开发。联邦学习是无线通信的一个新兴应用,该项目有可能推动这一新用例的技术开发。同时,理论基础、算法和验证将广泛推进机器学习、通信理论和无线网络的最新发展。开发这种实用和有影响力的技术也将有助于保持美国在无线技术方面的领导地位,并保持供应高质量,训练有素和创新的工程师的管道。该项目追求协同活动,以成功设计和实施无线FL的资源配给。在每个学习回合中,对FL进行不同资源的新收敛分析,这就确立了一般的“后来者更好”原则。在理论基础的指导下,该项目进一步构建了一个全面的算法框架,用于特定的资源配给设计,从物理层比特加载和自适应编码和调制到MAC层客户端选择,带宽分配,该奖项反映了NSF的法定使命,并通过使用基金会的知识价值和更广泛的影响审查进行评估,被认为值得支持的搜索.

项目成果

期刊论文数量(6)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Client Selection and Bandwidth Allocation in Wireless Federated Learning Networks: A Long-Term Perspective
Resource Rationing for Wireless Federated Learning: Concept, Benefits, and Challenges
  • DOI:
    10.1109/mcom.001.2000744
  • 发表时间:
    2021-04
  • 期刊:
  • 影响因子:
    11.2
  • 作者:
    Cong Shen;Jie Xu;Sihui Zheng;Xiang Chen
  • 通讯作者:
    Cong Shen;Jie Xu;Sihui Zheng;Xiang Chen
Context-Aware Online Client Selection for Hierarchical Federated Learning
Seek Common While Shelving Differences: Orchestrating Deep Neural Networks for Edge Service Provisioning
On Federated Learning with Energy Harvesting Clients
{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ monograph.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ sciAawards.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ conferencePapers.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ patent.updateTime }}

Jie Xu其他文献

Design Challenges and Guidelines for Persuasive Technologies that Facilitate Healthy Lifestyles.
促进健康生活方式的说服性技术的设计挑战和指南。
On demand generation of drop and bubble in a microfluidic chip
微流控芯片中按需生成液滴和气泡
  • DOI:
  • 发表时间:
    2008
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Jie Xu;Daniel Attinger
  • 通讯作者:
    Daniel Attinger
Structure and Properties of Ultrathin SiOx Films on Cu(111)
Cu(111)上超薄SiOx薄膜的结构与性能
  • DOI:
    10.1021/acs.langmuir.2c01701
  • 发表时间:
    2022
  • 期刊:
  • 影响因子:
    3.9
  • 作者:
    Jie Xu;Changle Mu;Mingshu Chen
  • 通讯作者:
    Mingshu Chen
Designing messages with high sensation value: When activation meets reactance
设计具有高感觉价值的消息:当激活遇到抗拒时
  • DOI:
    10.1080/08870446.2014.977280
  • 发表时间:
    2015
  • 期刊:
  • 影响因子:
    3.3
  • 作者:
    Jie Xu
  • 通讯作者:
    Jie Xu
Well dispersive Ni nanoparticles embedded in core-shell supports as efficient catalysts for 4-nitrophenol reduction
嵌入核壳载体中的分散性良好的镍纳米粒子作为 4-硝基苯酚还原的有效催化剂
  • DOI:
    10.1007/s11051-019-4551-0
  • 发表时间:
    2019-06
  • 期刊:
  • 影响因子:
    2.5
  • 作者:
    Xiaoshan Yang;Zhenwei Wang;Yuanyuan Shang;Yingjiu Zhang;Qing Lou;Baojun Li;Jie Xu
  • 通讯作者:
    Jie Xu

Jie Xu的其他文献

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

{{ truncateString('Jie Xu', 18)}}的其他基金

Elucidating Mechanisms of Metal Sulfide-Enabled Growth of Anoxygenic Photosynthetic Bacteria Using Transcriptomic, Aqueous/Surface Chemical, and Electron Microscopic Tools
使用转录组、水/表面化学和电子显微镜工具阐明金属硫化物促进不产氧光合细菌生长的机制
  • 批准号:
    2311021
  • 财政年份:
    2023
  • 资助金额:
    $ 20万
  • 项目类别:
    Standard Grant
Collaborative Research: CCSS: Hierarchical Federated Learning over Highly-Dense and Overlapping NextG Wireless Deployments: Orchestrating Resources for Performance
协作研究:CCSS:高密度和重叠的 NextG 无线部署的分层联合学习:编排资源以提高性能
  • 批准号:
    2319780
  • 财政年份:
    2023
  • 资助金额:
    $ 20万
  • 项目类别:
    Standard Grant
SAI-R: Strengthening American Electricity Infrastructure for an Electric Vehicle Future: An Energy Justice Approach
SAI-R:加强美国电力基础设施以实现电动汽车的未来:能源正义方法
  • 批准号:
    2228603
  • 财政年份:
    2022
  • 资助金额:
    $ 20万
  • 项目类别:
    Standard Grant
CAREER: Wireless InferNets: Enabling Collaborative Machine Learning Inference on the Network Path
职业:无线推理网:在网络路径上实现协作机器学习推理
  • 批准号:
    2044991
  • 财政年份:
    2021
  • 资助金额:
    $ 20万
  • 项目类别:
    Continuing Grant
Collaborative Research: SWIFT: SMALL: Understanding and Combating Adversarial Spectrum Learning towards Spectrum-Efficient Wireless Networking
合作研究:SWIFT:SMALL:理解和对抗对抗性频谱学习以实现频谱高效的无线网络
  • 批准号:
    2029858
  • 财政年份:
    2020
  • 资助金额:
    $ 20万
  • 项目类别:
    Standard Grant
Collaborative Research: CNS Core: Small: Towards Automated and QoE-driven Machine Learning Model Selection for Edge Inference
合作研究:CNS 核心:小型:面向边缘推理的自动化和 QoE 驱动的机器学习模型选择
  • 批准号:
    2006630
  • 财政年份:
    2020
  • 资助金额:
    $ 20万
  • 项目类别:
    Standard Grant
Collaborative Research: Improving Power Grids Weather Resilience through Model-free Dimension Reduction and Stochastic Search for Optimal Hardening
合作研究:通过无模型降维和随机搜索优化强化来提高电网的耐候能力
  • 批准号:
    1923145
  • 财政年份:
    2019
  • 资助金额:
    $ 20万
  • 项目类别:
    Standard Grant
Collaborative Research: Towards High-Throughput Label-Free Circulating Tumor Cell Separation using 3D Deterministic Dielectrophoresis (D-Cubed)
合作研究:利用 3D 确定性介电泳 (D-Cubed) 实现高通量无标记循环肿瘤细胞分离
  • 批准号:
    1917295
  • 财政年份:
    2019
  • 资助金额:
    $ 20万
  • 项目类别:
    Standard Grant
Collaborative Research: NSF/ENG/ECCS-BSF: Complex liquid droplet structures as new optical and optomechanical materials
合作研究:NSF/ENG/ECCS-BSF:复杂液滴结构作为新型光学和光机械材料
  • 批准号:
    1711798
  • 财政年份:
    2017
  • 资助金额:
    $ 20万
  • 项目类别:
    Standard Grant
EAGER-Dynamic Data: A New Scalable Paradigm for Optimal Resource Allocation in Dynamic Data Systems via Multi-Scale and Multi-Fidelity Simulation and Optimization
EAGER-动态数据:通过多尺度和多保真度仿真和优化实现动态数据系统中最佳资源分配的新可扩展范式
  • 批准号:
    1462409
  • 财政年份:
    2015
  • 资助金额:
    $ 20万
  • 项目类别:
    Standard Grant

相似海外基金

Collaborative Research: ECCS-CCSS Core: Resonant-Beam based Optical-Wireless Communication
合作研究:ECCS-CCSS核心:基于谐振光束的光无线通信
  • 批准号:
    2332172
  • 财政年份:
    2024
  • 资助金额:
    $ 20万
  • 项目类别:
    Standard Grant
Collaborative Research: ECCS-CCSS Core: Resonant-Beam based Optical-Wireless Communication
合作研究:ECCS-CCSS核心:基于谐振光束的光无线通信
  • 批准号:
    2332173
  • 财政年份:
    2024
  • 资助金额:
    $ 20万
  • 项目类别:
    Standard Grant
Collaborative Research: CCSS: Continuous Facial Sensing and 3D Reconstruction via Single-ear Wearable Biosensors
合作研究:CCSS:通过单耳可穿戴生物传感器进行连续面部传感和 3D 重建
  • 批准号:
    2401415
  • 财政年份:
    2023
  • 资助金额:
    $ 20万
  • 项目类别:
    Standard Grant
Collaborative Research: CCSS: When RFID Meets AI for Occluded Body Skeletal Posture Capture in Smart Healthcare
合作研究:CCSS:当 RFID 与人工智能相遇,用于智能医疗保健中闭塞的身体骨骼姿势捕获
  • 批准号:
    2245607
  • 财政年份:
    2023
  • 资助金额:
    $ 20万
  • 项目类别:
    Standard Grant
Collaborative Research: CCSS: Hierarchical Federated Learning over Highly-Dense and Overlapping NextG Wireless Deployments: Orchestrating Resources for Performance
协作研究:CCSS:高密度和重叠的 NextG 无线部署的分层联合学习:编排资源以提高性能
  • 批准号:
    2319780
  • 财政年份:
    2023
  • 资助金额:
    $ 20万
  • 项目类别:
    Standard Grant
Collaborative Research: CCSS: Hierarchical Federated Learning over Highly-Dense and Overlapping NextG Wireless Deployments: Orchestrating Resources for Performance
协作研究:CCSS:高密度和重叠的 NextG 无线部署的分层联合学习:编排资源以提高性能
  • 批准号:
    2319781
  • 财政年份:
    2023
  • 资助金额:
    $ 20万
  • 项目类别:
    Standard Grant
Collaborative Research: CCSS: Towards Energy-Efficient Millimeter Wave Wireless Networks: A Unified Systems and Circuits Framework
合作研究:CCSS:迈向节能毫米波无线网络:统一系统和电路框架
  • 批准号:
    2242700
  • 财政年份:
    2023
  • 资助金额:
    $ 20万
  • 项目类别:
    Standard Grant
Collaborative Research: CCSS: When RFID Meets AI for Occluded Body Skeletal Posture Capture in Smart Healthcare
合作研究:CCSS:当 RFID 与人工智能相遇,用于智能医疗保健中闭塞的身体骨骼姿势捕获
  • 批准号:
    2245608
  • 财政年份:
    2023
  • 资助金额:
    $ 20万
  • 项目类别:
    Standard Grant
Collaborative Research: CCSS: Towards Energy-Efficient Millimeter Wave Wireless Networks: A Unified Systems and Circuits Framework
合作研究:CCSS:迈向节能毫米波无线网络:统一系统和电路框架
  • 批准号:
    2242701
  • 财政年份:
    2023
  • 资助金额:
    $ 20万
  • 项目类别:
    Standard Grant
CCSS: Collaborative Research: Quickest Threat Detection in Adversarial Sensor Networks
CCSS:协作研究:对抗性传感器网络中最快的威胁检测
  • 批准号:
    2236565
  • 财政年份:
    2022
  • 资助金额:
    $ 20万
  • 项目类别:
    Standard Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了