Collaborative Research: MLWiNS: A Coding-Centric Approach to Robust, Secure, and Private Distributed Learning over Wireless
协作研究:MLWiNS:一种以编码为中心的方法,通过无线实现稳健、安全和私密的分布式学习
基本信息
- 批准号:2002874
- 负责人:
- 金额:$ 13.33万
- 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:2020-06-01 至 2023-05-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Human and industrial automation, powered by machine learning (ML) such as Deep Neural Networks (DNNs) and the burgeoning ecosystem of billions of edge computing devices with sensors connected through the infrastructure of the internet (i.e., Internet of Things, or IoT) is shaping the future of our society. Federated learning (also known as, collaborative learning) techniques work across multiple decentralized edge devices and/or servers holding local data samples and facilitate training of the algorithms by exchanging parameters (i.e., weights associated with deep networks) instead of the actual data samples. Federated learning over wireless networks is challenging because of data loss associated with the communication characteristics. The goal of this project is to provide their critically needed augmented intelligence by enabling federated learning at the wireless edge, via an innovative framework, named coded computing. The societal impact of democratizing machine learning on low cost edge devices is also expected to be vast. For instance, smart edge networks that track safety automatically and continuously in workplaces can have a significant societal and economic impact. This project paves the path towards scalable realization of such applications.Coded computing has been hugely successful for large-scale distributed machine learning, where one can judiciously create computational redundancy in a coded manner to efficiently deal with communication bottleneck and system disturbances such as stragglers, outages, node failures, and adversarial computations -- precisely the set of challenges that hobble distributed wireless edge computations for machine learning. This project leads to the development of theory and algorithms for federated machine learning over wireless that are driven by fundamental principles informed by coding and information theory. In particular, this project holistically addresses the challenges of (i) wireless bandwidth costs, (ii) resiliency to wireless outages, (iii) security, and (iv) prioritizing user data privacy that is critical for large-scale user participation in wireless edge computing. Another key aspect of wireless networks is that mobile users join and leave the network arbitrarily, and user locations can change frequently. The research team will develop a federated learning framework that can adapt to such dynamic network topologies by designing a self-configurable protocol that can accommodate new users on-the-go, thereby adapting to the changes in the network topology.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.
人类和工业自动化,由深度神经网络(DNN)等机器学习(ML)和数十亿边缘计算设备组成的蓬勃发展的生态系统提供支持,这些设备具有通过互联网基础设施连接的传感器(即,物联网(IoT)正在塑造我们社会的未来。联合学习(也称为协作学习)技术在多个分散的边缘设备和/或保存本地数据样本的服务器上工作,并且通过交换参数(即,与深度网络相关联的权重)而不是实际数据样本。由于与通信特性相关的数据丢失,无线网络上的联邦学习具有挑战性。该项目的目标是通过一个名为编码计算的创新框架,在无线边缘实现联合学习,从而提供他们急需的增强智能。机器学习在低成本边缘设备上的民主化也将产生巨大的社会影响。例如,在工作场所自动持续跟踪安全的智能边缘网络可以产生重大的社会和经济影响。编码计算在大规模分布式机器学习中取得了巨大的成功,人们可以明智地以编码的方式创建计算冗余,以有效地处理通信瓶颈和系统干扰,如掉队,中断,节点故障,和对抗性计算--正是这些挑战阻碍了机器学习的分布式无线边缘计算。 该项目导致了无线联合机器学习的理论和算法的发展,这些理论和算法由编码和信息理论的基本原理驱动。特别是,该项目全面解决了以下挑战:(i)无线带宽成本,(ii)无线中断的弹性,(iii)安全性,以及(iv)优先考虑用户数据隐私,这对于大规模用户参与无线边缘计算至关重要。无线网络的另一个关键方面是,移动的用户可以任意加入和离开网络,并且用户位置可以频繁改变。该研究团队将开发一个联邦学习框架,通过设计一个可自配置的协议来适应这种动态网络拓扑结构,该协议可以随时容纳新用户,从而适应网络拓扑结构的变化。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标准进行评估,被认为值得支持。
项目成果
期刊论文数量(7)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Coded Computing for Low-Latency Federated Learning Over Wireless Edge Networks
- DOI:10.1109/jsac.2020.3036961
- 发表时间:2020-11
- 期刊:
- 影响因子:16.4
- 作者:Saurav Prakash;S. Dhakal;M. Akdeniz;Yair Yona;S. Talwar;S. Avestimehr;N. Himayat
- 通讯作者:Saurav Prakash;S. Dhakal;M. Akdeniz;Yair Yona;S. Talwar;S. Avestimehr;N. Himayat
LightSecAgg: a Lightweight and Versatile Design for Secure Aggregation in Federated Learning
- DOI:
- 发表时间:2021-09
- 期刊:
- 影响因子:0
- 作者:Jinhyun So;Chaoyang He;Chien-Sheng Yang;Songze Li;Qian Yu;Ramy E. Ali;Basak Guler;S. Avestimehr
- 通讯作者:Jinhyun So;Chaoyang He;Chien-Sheng Yang;Songze Li;Qian Yu;Ramy E. Ali;Basak Guler;S. Avestimehr
Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge
- DOI:
- 发表时间:2020-07
- 期刊:
- 影响因子:0
- 作者:Chaoyang He;M. Annavaram;S. Avestimehr
- 通讯作者:Chaoyang He;M. Annavaram;S. Avestimehr
Private Retrieval, Computing, and Learning: Recent Progress and Future Challenges
- DOI:10.1109/jsac.2022.3142358
- 发表时间:2021-07
- 期刊:
- 影响因子:16.4
- 作者:S. Ulukus;S. Avestimehr;M. Gastpar;S. Jafar;R. Tandon;Chao Tian
- 通讯作者:S. Ulukus;S. Avestimehr;M. Gastpar;S. Jafar;R. Tandon;Chao Tian
Adaptive Verifiable Coded Computing: Towards Fast, Secure and Private Distributed Machine Learning
- DOI:10.1109/ipdps53621.2022.00067
- 发表时间:2021-07
- 期刊:
- 影响因子:0
- 作者:Ting-long Tang;Ramy E. Ali;H. Hashemi;Tynan Gangwani;A. Avestimehr;M. Annavaram
- 通讯作者:Ting-long Tang;Ramy E. Ali;H. Hashemi;Tynan Gangwani;A. Avestimehr;M. Annavaram
{{
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 }}
Amir Avestimehr其他文献
Amir Avestimehr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('Amir Avestimehr', 18)}}的其他基金
CIF: Student Travel Grant for the 2020 IEEE International Symposium on Information Theory (ISIT)
CIF:2020 年 IEEE 国际信息论研讨会 (ISIT) 学生旅费补助金
- 批准号:
1954152 - 财政年份:2020
- 资助金额:
$ 13.33万 - 项目类别:
Standard Grant
CIF: Medium: Collaborative Research: Coded Computing for Large-Scale Machine Learning
CIF:媒介:协作研究:大规模机器学习的编码计算
- 批准号:
1763673 - 财政年份:2018
- 资助金额:
$ 13.33万 - 项目类别:
Continuing Grant
CIF:Medium:Collaborative Research: Foundations of Coding for Modern Distributed Computing
CIF:中:协作研究:现代分布式计算编码基础
- 批准号:
1703575 - 财政年份:2017
- 资助金额:
$ 13.33万 - 项目类别:
Continuing Grant
CIF: Medium: Collaborative Research: Multihop Multiflow Wireless Networks: A Treasure Hunt
CIF:媒介:协作研究:多跳多流无线网络:寻宝
- 批准号:
1408755 - 财政年份:2014
- 资助金额:
$ 13.33万 - 项目类别:
Standard Grant
CAREER: Breaking the Barriers in Wireless Network Information Theory: A Deterministic Approach
职业:打破无线网络信息理论的障碍:确定性方法
- 批准号:
1408639 - 财政年份:2014
- 资助金额:
$ 13.33万 - 项目类别:
Continuing Grant
EARS: Interference-Aware RF Theory and Design
EARS:干扰感知射频理论和设计
- 批准号:
1411244 - 财政年份:2014
- 资助金额:
$ 13.33万 - 项目类别:
Standard Grant
NeTS: Medium: Collaborative Research: Information Architectures for Femto-Aided Cellular Networks
NeTS:媒介:协作研究:毫微微辅助蜂窝网络的信息架构
- 批准号:
1419632 - 财政年份:2014
- 资助金额:
$ 13.33万 - 项目类别:
Continuing Grant
EARS: Interference-Aware RF Theory and Design
EARS:干扰感知射频理论和设计
- 批准号:
1247915 - 财政年份:2013
- 资助金额:
$ 13.33万 - 项目类别:
Standard Grant
NeTS: Medium: Collaborative Research: Information Architectures for Femto-Aided Cellular Networks
NeTS:媒介:协作研究:毫微微辅助蜂窝网络的信息架构
- 批准号:
1161904 - 财政年份:2012
- 资助金额:
$ 13.33万 - 项目类别:
Continuing Grant
CIF: Medium: Collaborative Research: Multihop Multiflow Wireless Networks: A Treasure Hunt
CIF:媒介:协作研究:多跳多流无线网络:寻宝
- 批准号:
1161720 - 财政年份:2012
- 资助金额:
$ 13.33万 - 项目类别:
Standard Grant
相似国自然基金
复杂电子产品超精密加工及检测关键技术研究与应用
- 批准号:
- 批准年份:2025
- 资助金额:0.0 万元
- 项目类别:省市级项目
基于合成生物学的动物底盘品种优化及中试应用研究
- 批准号:
- 批准年份:2025
- 资助金额:0.0 万元
- 项目类别:省市级项目
运用组学整合技术探索萆薢分清散联合化疗治疗晚期胰腺癌的临床研究
- 批准号:
- 批准年份:2025
- 资助金额:0.0 万元
- 项目类别:省市级项目
九里香等提取物多靶向制剂抗肺癌的作用及机制研究
- 批准号:
- 批准年份:2025
- 资助金额:0.0 万元
- 项目类别:省市级项目
升血小板方治疗原发免疫性血小板减少症的临床研究
- 批准号:
- 批准年份:2025
- 资助金额:0.0 万元
- 项目类别:省市级项目
八髎穴微波热疗在女性膀胱过度活动症治疗中的价值研究
- 批准号:
- 批准年份:2025
- 资助金额:0.0 万元
- 项目类别:省市级项目
基于 miR-455-5p 介导的氧化应激机制探讨糖尿病视网膜病变中医分型治疗的临床研究
- 批准号:
- 批准年份:2025
- 资助金额:0.0 万元
- 项目类别:省市级项目
基于 UPLC-Q-TOF-MS/MS 分析的 异功散活性成分评价及提取工艺研究
- 批准号:
- 批准年份:2025
- 资助金额:0.0 万元
- 项目类别:省市级项目
无创电针对于痉挛型双瘫脑 瘫患儿的有效性与安全性研究:一项随机 单盲前瞻性队列研究
- 批准号:
- 批准年份:2025
- 资助金额:0.0 万元
- 项目类别:省市级项目
弹压式手法与体外冲击波治疗肱骨外上髁炎的对比研究
- 批准号:
- 批准年份:2025
- 资助金额:0.0 万元
- 项目类别:省市级项目
相似海外基金
Collaborative Research: MLWiNS: Distributed Learning over Multi-Access Channels: From Bandlimited Coordinate Descent to Gradient Sketching
协作研究:MLWiNS:多访问通道上的分布式学习:从带限坐标下降到梯度草图
- 批准号:
2203412 - 财政年份:2021
- 资助金额:
$ 13.33万 - 项目类别:
Standard Grant
Collaborative Research: MLWiNS: A Coding-Centric Approach to Robust, Secure, and Private Distributed Learning over Wireless
协作研究:MLWiNS:一种以编码为中心的方法,通过无线实现稳健、安全和私密的分布式学习
- 批准号:
2002821 - 财政年份:2020
- 资助金额:
$ 13.33万 - 项目类别:
Standard Grant
Collaborative Research: MLWiNS: Distributed Learning over Multi-Access Channels: From Bandlimited Coordinate Descent to Gradient Sketching
协作研究:MLWiNS:多访问通道上的分布式学习:从带限坐标下降到梯度草图
- 批准号:
2003081 - 财政年份:2020
- 资助金额:
$ 13.33万 - 项目类别:
Standard Grant
Collaborative Research: MLWiNS: Dino-RL: A Domain Knowledge Enriched Reinforcement Learning Framework for Wireless Network Optimization
合作研究:MLWiNS:Dino-RL:用于无线网络优化的领域知识丰富的强化学习框架
- 批准号:
2002902 - 财政年份:2020
- 资助金额:
$ 13.33万 - 项目类别:
Standard Grant
Collaborative Research: MLWiNS: ANN for Interference Limited Wireless Networks
合作研究:MLWiNS:干扰有限无线网络的 ANN
- 批准号:
2003098 - 财政年份:2020
- 资助金额:
$ 13.33万 - 项目类别:
Standard Grant
Collaborative Research: MLWiNS: Distributed Learning over Multi-Access Channels: From Bandlimited Coordinate Descent to Gradient Sketching
协作研究:MLWiNS:多访问通道上的分布式学习:从带限坐标下降到梯度草图
- 批准号:
2003111 - 财政年份:2020
- 资助金额:
$ 13.33万 - 项目类别:
Standard Grant
Collaborative Research: MLWiNS: Dino-RL: A Domain Knowledge Enriched Reinforcement Learning Framework for Wireless Network Optimization
合作研究:MLWiNS:Dino-RL:用于无线网络优化的领域知识丰富的强化学习框架
- 批准号:
2003131 - 财政年份:2020
- 资助金额:
$ 13.33万 - 项目类别:
Standard Grant
Collaborative Research: MLWiNS: Hyperdimensional Computing for Scalable IoT Intelligence Beyond the Edge
协作研究:MLWiNS:用于超越边缘的可扩展物联网智能的超维计算
- 批准号:
2003279 - 财政年份:2020
- 资助金额:
$ 13.33万 - 项目类别:
Standard Grant
Collaborative Research: MLWiNS: ANN for Interference Limited Wireless Networks
合作研究:MLWiNS:干扰有限无线网络的 ANN
- 批准号:
2003082 - 财政年份:2020
- 资助金额:
$ 13.33万 - 项目类别:
Standard Grant
Collaborative Research: MLWiNS: Physical Layer Communication revisited via Deep Learning
合作研究:MLWiNS:通过深度学习重新审视物理层通信
- 批准号:
2002664 - 财政年份:2020
- 资助金额:
$ 13.33万 - 项目类别:
Standard Grant