CAREER: Ubiquitous and Time-Critical Federated Learning with Cooperative Mobile Edge Networking

职业:具有协作移动边缘网络的无处不在且时间紧迫的联合学习

基本信息

  • 批准号:
    2047761
  • 负责人:
  • 金额:
    $ 50.9万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Continuing Grant
  • 财政年份:
    2021
  • 资助国家:
    美国
  • 起止时间:
    2021-10-01 至 2026-09-30
  • 项目状态:
    未结题

项目摘要

Federated learning (FL) enables Internet-of-Things (IoT) devices at the network edge to collaboratively learn a shared prediction model while keeping all personal data on the device. However, the current cloud-based FL fails to meet the latency requirements of delay-sensitive IoT applications due to the long-distance transmission between IoT devices and the cloud. This project aims to enable ubiquitous and time-critical FL at the wireless edge to support delay-sensitive and data-driven IoT applications. The project will fulfill the needs of many compelling applications with significant economic and societal impacts such as augmented reality, autonomous driving, mobile healthcare, and smart manufacturing. The project’s educational agenda includes outreach to K-12 with educational summer camps for high-school teachers, mentoring undergraduate and graduate students, especially from minority and underrepresented groups, in the research, and disseminating research outcomes to students and industry partners through new course development and seminars.This project develops a novel Federated learning (FL) framework based on cooperative mobile edge networking that can efficiently support learning and decision making on distributed Internet-of-Things (IoT) data with high accuracy, low latency, and guaranteed privacy. Three interconnected research thrusts are investigated in this project: 1) design of novel network-aware learning algorithms under a two-level network structure to ensure efficient and effective model training from decentralized data on IoT devices over wireless edge networks; 2) jointly optimize resource allocation and learning based on deep reinforcement learning to learn an accurate model rapidly under system heterogeneity and resource constraints; 3) develop novel differential privacy techniques to rigorously protect the privacy of personal data on IoT devices while maintaining high model accuracy and reducing communication cost. The proposed research will enable next-generation wireless edge networks that support a plethora of delay-sensitive and data-driven IoT applications. The proposed research will benefit not only the wireless networking but also machine learning research communities by bridging the gap between the evolving mobile computing and networking technologies and rapidly advancing machine learning techniques.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.
联合学习(FL)使网络边缘的物联网(IoT)设备能够协作学习共享预测模型,同时将所有个人数据保存在设备上。然而,由于物联网设备和云端之间的长距离传输,目前基于云的FL无法满足延迟敏感的物联网应用的延迟要求。该项目旨在在无线边缘实现无处不在和时间关键的FL,以支持延迟敏感和数据驱动的物联网应用。该项目将满足许多具有重大经济和社会影响的引人注目的应用的需求,如增强现实,自动驾驶,移动的医疗保健和智能制造。该项目的教育议程包括通过为高中教师举办教育夏令营,指导本科生和研究生,特别是来自少数民族和代表性不足群体的学生,并通过新课程开发和研讨会向学生和行业合作伙伴传播研究成果。该项目开发了一种新的联邦学习(FL)基于协作式移动的边缘网络的框架,可以高效地支持对分布式物联网(IoT)数据的学习和决策,具有高准确性、低延迟和有保障的隐私。本项目主要研究三个相互关联的研究方向:1)设计两级网络结构下的新型网络感知学习算法,确保在无线边缘网络上从物联网设备上的分散数据进行高效的模型训练; 2)联合优化资源分配和基于深度强化学习的学习,在系统异构和资源受限的情况下快速学习准确的模型; 3)开发新的差分隐私技术,严格保护物联网设备上的个人数据隐私,同时保持高模型准确性并降低通信成本。拟议的研究将使下一代无线边缘网络能够支持大量延迟敏感和数据驱动的物联网应用。拟议的研究将不仅有利于无线网络,也有利于机器学习研究社区,通过弥合不断发展的移动的计算和网络技术与快速发展的机器学习技术之间的差距。该奖项反映了NSF的法定使命,并已被认为值得通过使用基金会的智力价值和更广泛的影响审查标准进行评估来支持。

项目成果

期刊论文数量(5)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Energy-Efficient Distributed Machine Learning at Wireless Edge with Device-to-Device Communication
Agent-Level Differentially Private Federated Learning via Compressed Model Perturbation
Scalable and Low-Latency Federated Learning With Cooperative Mobile Edge Networking
  • DOI:
    10.1109/tmc.2022.3216837
  • 发表时间:
    2022-05
  • 期刊:
  • 影响因子:
    7.9
  • 作者:
    Zhenxiao Zhang;Zhidong Gao;Yuanxiong Guo;Yanmin Gong
  • 通讯作者:
    Zhenxiao Zhang;Zhidong Gao;Yuanxiong Guo;Yanmin Gong
Concentrated Differentially Private Federated Learning With Performance Analysis
  • DOI:
    10.1109/ojcs.2021.3099108
  • 发表时间:
    2021
  • 期刊:
  • 影响因子:
    5.9
  • 作者:
    Rui Hu;Yuanxiong Guo;Yanmin Gong
  • 通讯作者:
    Rui Hu;Yuanxiong Guo;Yanmin Gong
{{ 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 }}

Yanmin Gong其他文献

Practical Collaborative Learning for Crowdsensing in the Internet of Things with Differential Privacy
具有差异隐私的物联网中群体感知的实用协作学习
Efficient, Effective, and Realistic Website Fingerprinting Mitigation
高效、有效且现实的网站指纹识别缓解
A stochastic game approach to cyber-physical security with applications to smart grid
网络物理安全的随机博弈方法及其在智能电网中的应用
Supplementary Material of Workie-Talkie: Accelerating Federated Learning by Overlapping Computing and Communications via Contrastive Regularization
Workie-Talkie 补充材料:通过对比正则化重叠计算和通信来加速联邦学习
  • DOI:
  • 发表时间:
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Rui Chen;Qiyu Wan;Pavana Prakash;Lan Zhang;Xu Yuan;Yanmin Gong;Xin Fu;Miao Pan
  • 通讯作者:
    Miao Pan
Quasi-convex Optimization of Metrics in Biometric Score Fusion
生物特征得分融合中指标的拟凸优化

Yanmin Gong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('Yanmin Gong', 18)}}的其他基金

CRII: NeTS: Embracing Dynamic Spectrum Sharing without Privacy Concerns
CRII:NeTS:拥抱动态频谱共享,无需担心隐私问题
  • 批准号:
    1850523
  • 财政年份:
    2019
  • 资助金额:
    $ 50.9万
  • 项目类别:
    Standard Grant

相似海外基金

Development of an ubiquitous diagnostic system of trombosis available at the time of emergency disaster
开发紧急灾害时可使用的普遍存在的血栓诊断系统
  • 批准号:
    20K04507
  • 财政年份:
    2020
  • 资助金额:
    $ 50.9万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
MAGIC - an integrated platform for mobile payments and real-time marketing based on Bluetooth Low Energy ubiquitous to Smartphones
MAGIC - 基于智能手机普遍存在的低功耗蓝牙的移动支付和实时营销集成平台
  • 批准号:
    102550
  • 财政年份:
    2016
  • 资助金额:
    $ 50.9万
  • 项目类别:
    Collaborative R&D
Organic Computing Techniques for Run-Time Self-Adaptation of Ubiquitous, Multi-Modal Activity Recognition Systems
用于普遍存在的多模态活动识别系统运行时自适应的有机计算技术
  • 批准号:
    276698135
  • 财政年份:
    2015
  • 资助金额:
    $ 50.9万
  • 项目类别:
    Research Grants
UbiquiSon - Ubiquitous ultrasound; machines within the reach of every clinician, all the time.
UbiquiSon - 无处不在的超声波;
  • 批准号:
    131627
  • 财政年份:
    2014
  • 资助金额:
    $ 50.9万
  • 项目类别:
    Feasibility Studies
CPS: Synergy: Collaborative Research: SensEye: An Architecture for Ubiquitous, Real-Time Visual Context Ssensing and Inference
CPS:协同:协作研究:SensEye:无处不在的实时视觉上下文感知和推理架构
  • 批准号:
    1239341
  • 财政年份:
    2012
  • 资助金额:
    $ 50.9万
  • 项目类别:
    Standard Grant
CPS: Synergy: Collaborative Research: SensEye: An Architecture for Ubiquitous, Real-Time Visual Context Sensing and Inference
CPS:协同:协作研究:SensEye:无处不在的实时视觉上下文感知和推理架构
  • 批准号:
    1239031
  • 财政年份:
    2012
  • 资助金额:
    $ 50.9万
  • 项目类别:
    Standard Grant
Secure and Ubiquitous Hospital Information System Infrastructure by Real-time Location System and Virtualization Technology
通过实时定位系统和虚拟化技术构建安全、无处不在的医院信息系统基础设施
  • 批准号:
    23590583
  • 财政年份:
    2011
  • 资助金额:
    $ 50.9万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
Ubiquitous and socially-aware real-time urban computing platform
无处不在且具有社会意识的实时城市计算平台
  • 批准号:
    298238-2010
  • 财政年份:
    2011
  • 资助金额:
    $ 50.9万
  • 项目类别:
    Discovery Grants Program - Individual
Ubiquitous and socially-aware real-time urban computing platform
无处不在且具有社会意识的实时城市计算平台
  • 批准号:
    298238-2010
  • 财政年份:
    2010
  • 资助金额:
    $ 50.9万
  • 项目类别:
    Discovery Grants Program - Individual
Real-time network simulation for large-scale ubiquitous network
大规模泛在网络实时网络仿真
  • 批准号:
    20240006
  • 财政年份:
    2008
  • 资助金额:
    $ 50.9万
  • 项目类别:
    Grant-in-Aid for Scientific Research (A)
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了