CCSS: Distributed Swarm Learning for Internet of Things at the Edge
CCSS:边缘物联网的分布式群体学习
基本信息
- 批准号:2231209
- 负责人:
- 金额:$ 40万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Standard Grant
- 财政年份:2023
- 资助国家:美国
- 起止时间:2023-01-01 至 2025-12-31
- 项目状态:未结题
- 来源:
- 关键词:
项目摘要
With the vigorous growth of versatile Internet of Things (IoT) services, smart IoT devices are increasingly deployed at the edge of wireless IoT networks to perform collaborative machine learning tasks using locally collected data, giving rise to the edge learning paradigm. Because IoT networks have massive low-cost edge devices with limited capabilities and resources, IoT-driven edge learning faces major technical challenges caused by the communication bottleneck, data and device heterogeneity, non-convex optimization, privacy and security concerns, and dynamic operating environments. To overcome these challenges, this project builds a new framework of distributed swarm learning (DSL) through a holistic integration of artificial intelligence and biological swarm intelligence. The proposed DSL framework for edge learning is expected to benefit a wide range of IoT applications such as autonomous fleet management, massive wearable electronics, smart agriculture, to name a few. This project also provides broader societal impacts through student training, workforce development, research dissemination and outreach to minorities and local communities.This objective of this project is to develop an efficient distributed learning framework that coherently addresses the unique technical challenges related to swarm IoT with device restrictions and resource constraints on communication, computation and data, and in complicated edge environments with potential link failure, attacks, and topology changes. First, a new DSL framework is established by bridging federated learning with swarm optimization techniques. With theoretical backing, efficient information extraction and exchanging mechanisms are developed along with parsimonious transmission schemes for high efficiency in both communication and computation of model updates. Second, to cope with data heterogeneity, link failure and malicious attacks in practical IoT systems, robust DSL techniques are developed based on generative adversarial networks, multi-worker selection and analog transmission-and-aggregation techniques. Finally, to handle streaming data in an online fashion at the network edge, dynamic optimization techniques are investigated via the design of adaptive weights and exploration-exploitation strategies under the DSL framework. The outcomes of this research are expected to contribute to novel tools for learning and optimization tailored to real-time operation of large-scale IoT in dynamic environments, with technological impacts on statistical learning, signal processing and wireless communications.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.
随着通用物联网(IoT)服务的蓬勃发展,智能物联网设备越来越多地部署在无线物联网网络的边缘,以使用本地收集的数据执行协作机器学习任务,从而产生了边缘学习范式。由于物联网网络拥有大量低成本的边缘设备,而这些设备的能力和资源有限,因此物联网驱动的边缘学习面临着通信瓶颈、数据和设备异构性、非凸优化、隐私和安全问题以及动态操作环境所带来的重大技术挑战。为了克服这些挑战,该项目通过人工智能和生物群体智能的整体集成,建立了一个新的分布式群体学习(DSL)框架。拟议的边缘学习DSL框架预计将有利于广泛的物联网应用,例如自主车队管理、大规模可穿戴电子产品、智能农业等。该项目还通过学生培训、劳动力发展、研究传播以及对少数民族和当地社区的外展来产生更广泛的社会影响。该项目的目标是开发一个有效的分布式学习框架,以协调一致地解决与群物联网相关的独特技术挑战,包括设备限制和通信、计算和数据的资源限制,以及在具有潜在链路故障、攻击和拓扑变化的复杂边缘环境中。首先,一个新的DSL框架,建立了一个桥梁联邦学习与群优化技术。在理论支持下,开发了有效的信息提取和交换机制,沿着开发了节约的传输方案,以提高模型更新的通信和计算效率。其次,为了科普实际物联网系统中的数据异构性,链路故障和恶意攻击,基于生成对抗网络,多工作者选择和模拟传输和聚合技术开发了鲁棒DSL技术。最后,在DSL框架下,通过设计自适应权重和探索-利用策略,研究了在网络边缘以在线方式处理流数据的动态优化技术。该研究成果有望为动态环境中大规模物联网的实时运行提供新的学习和优化工具,并对统计学习、信号处理和无线通信产生技术影响。该奖项反映了NSF的法定使命,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(4)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Robust Distributed Swarm Learning for Intelligent IoT
- DOI:10.1109/icc45041.2023.10278708
- 发表时间:2023-05
- 期刊:
- 影响因子:0
- 作者:Xin Fan;Yue Wang;Yan Huo;Zhi Tian
- 通讯作者:Xin Fan;Yue Wang;Yan Huo;Zhi Tian
CB-DSL: Communication-Efficient and Byzantine-Robust Distributed Swarm Learning on Non-i.i.d. Data
- DOI:10.1109/tccn.2023.3312345
- 发表时间:2022-08
- 期刊:
- 影响因子:8.6
- 作者:Xin Fan;Yue Wang;Yan Huo;Zhi Tian
- 通讯作者:Xin Fan;Yue Wang;Yan Huo;Zhi Tian
Efficient Distributed Swarm Learning for Edge Computing
- DOI:10.1109/icc45041.2023.10279508
- 发表时间:2023-05
- 期刊:
- 影响因子:0
- 作者:Xin Fan;Yue Wang;Yan Huo;Zhi Tian
- 通讯作者:Xin Fan;Yue Wang;Yan Huo;Zhi Tian
H-nobs: Achieving Certified Fairness and Robustness in Distributed Learning on Heterogeneous Datasets
H-nobs:在异构数据集的分布式学习中实现经过认证的公平性和鲁棒性
- DOI:
- 发表时间:2023
- 期刊:
- 影响因子:0
- 作者:Zhou, Guanqiang;Xu, Ping;Wang, Yue;Tian, Zhi
- 通讯作者:Tian, Zhi
{{
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 }}
Zhi Tian其他文献
Salinibacterium hongtaonis sp. nov., isolated from faeces of Tibetan antelope (Pantholops hodgsonii) on the Qinghai-Tibet Plateau.
洪涛盐杆菌
- DOI:
10.1099/ijsem.0.003277 - 发表时间:
2019 - 期刊:
- 影响因子:2.8
- 作者:
Junqin Li;Shan Lu;D. Jin;Jing Yang;X. Lai;Gui Zhang;Zhi Tian;Wentao Zhu;Ji Pu;Xiaomin Wu;Ying Huang;Suping Wang;Jianguo Xu - 通讯作者:
Jianguo Xu
Paracoccus liaowanqingii sp. nov., isolated from Tibetan antelope (Pantholops hodgsonii).
辽湾清副球菌 sp.
- DOI:
10.1099/ijsem.0.003807 - 发表时间:
2020 - 期刊:
- 影响因子:2.8
- 作者:
Junqin Li;Shan Lu;D. Jin;Jing Yang;X. Lai;Yuyuan Huang;Zhi Tian;Kui Dong;Sihui Zhang;Wenjing Lei;Ji Pu;Gui Zhang;Xiaomin Wu;Ying Huang;Zhihong Ren;Suping Wang;Jianguo Xu - 通讯作者:
Jianguo Xu
Characterization and vaccination of two novel Schistosoma japonicum genes screened from a cercaria cDNA library
从尾蚴 cDNA 文库中筛选出的两个日本血吸虫新基因的表征和疫苗接种
- DOI:
10.1007/s00436-011-2505-2 - 发表时间:
2011 - 期刊:
- 影响因子:2
- 作者:
Zhi Tian;Shi;Shao;Xueqin Liu;D. Gao;Qi;Shu;Yun;Xi;Ying - 通讯作者:
Ying
The effect of methanol production and application in internal combustion engines on emissions in the context of carbon neutrality: A review
- DOI:
10.1016/j.fuel.2022.123902 - 发表时间:
2022-07-15 - 期刊:
- 影响因子:
- 作者:
Zhi Tian;Yang Wang;Xudong Zhen;Zengbin Liu - 通讯作者:
Zengbin Liu
Recovery Conditions of Sparse Signals Using Orthogonal Least Squares-Type Algorithms
使用正交最小二乘型算法恢复稀疏信号的条件
- DOI:
10.1109/tsp.2022.3208439 - 发表时间:
2022-01 - 期刊:
- 影响因子:5.4
- 作者:
Liyang Lu;Wenbo Xu;Yue Wang;Zhi Tian - 通讯作者:
Zhi Tian
Zhi Tian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('Zhi Tian', 18)}}的其他基金
Collaborative Research: SWIFT: Intelligent Dynamic Spectrum Access (IDEA): An Efficient Learning Approach to Enhancing Spectrum Utilization and Coexistence
合作研究:SWIFT:智能动态频谱接入 (IDEA):增强频谱利用和共存的有效学习方法
- 批准号:
2128596 - 财政年份:2022
- 资助金额:
$ 40万 - 项目类别:
Standard Grant
CIF: Small: Communication-efficient and robust learning from distributed data
CIF:小型:从分布式数据中进行高效通信和稳健学习
- 批准号:
1939553 - 财政年份:2020
- 资助金额:
$ 40万 - 项目类别:
Standard Grant
Workshop: Promoting Broader Impacts of Research on Electrical, Communications and Cyber Systems; Holiday Inn Hotel, Arlington, Virginia, May 12-13, 2016
研讨会:促进电气、通信和网络系统研究的更广泛影响;
- 批准号:
1641369 - 财政年份:2016
- 资助金额:
$ 40万 - 项目类别:
Standard Grant
EAGER: Energy-efficient Massive MIMO Processing for Millimeter-wave Communications
EAGER:用于毫米波通信的节能大规模 MIMO 处理
- 批准号:
1546604 - 财政年份:2015
- 资助金额:
$ 40万 - 项目类别:
Standard Grant
CAREER: Signal Processing Research in Ultra Wideband Communications
职业:超宽带通信中的信号处理研究
- 批准号:
0238174 - 财政年份:2003
- 资助金额:
$ 40万 - 项目类别:
Continuing Grant
相似国自然基金
Graphon mean field games with partial observation and application to failure detection in distributed systems
- 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
CAREER: Verifying Security and Privacy of Distributed Applications
职业:验证分布式应用程序的安全性和隐私
- 批准号:
2338317 - 财政年份:2024
- 资助金额:
$ 40万 - 项目类别:
Continuing Grant
CRII: AF: The Impact of Knowledge on the Performance of Distributed Algorithms
CRII:AF:知识对分布式算法性能的影响
- 批准号:
2348346 - 财政年份:2024
- 资助金额:
$ 40万 - 项目类别:
Standard Grant
Collaborative Research: AF: Medium: The Communication Cost of Distributed Computation
合作研究:AF:媒介:分布式计算的通信成本
- 批准号:
2402836 - 财政年份:2024
- 资助金额:
$ 40万 - 项目类别:
Continuing Grant
Collaborative Research: OAC Core: Distributed Graph Learning Cyberinfrastructure for Large-scale Spatiotemporal Prediction
合作研究:OAC Core:用于大规模时空预测的分布式图学习网络基础设施
- 批准号:
2403312 - 财政年份:2024
- 资助金额:
$ 40万 - 项目类别:
Standard Grant
Collaborative Research: An Integrated Framework for Learning-Enabled and Communication-Aware Hierarchical Distributed Optimization
协作研究:支持学习和通信感知的分层分布式优化的集成框架
- 批准号:
2331710 - 财政年份:2024
- 资助金额:
$ 40万 - 项目类别:
Standard Grant
Collaborative Research: An Integrated Framework for Learning-Enabled and Communication-Aware Hierarchical Distributed Optimization
协作研究:支持学习和通信感知的分层分布式优化的集成框架
- 批准号:
2331711 - 财政年份:2024
- 资助金额:
$ 40万 - 项目类别:
Standard Grant
Next-Generation Distributed Graph Engine for Big Graphs
适用于大图的下一代分布式图引擎
- 批准号:
DP240101322 - 财政年份:2024
- 资助金额:
$ 40万 - 项目类别:
Discovery Projects
New, easy to use, low-cost technologies based on DNA origami biosensing to achieve distributed screening for AMR and improved antibiotic prescribing
基于 DNA 折纸生物传感的易于使用、低成本的新型技术,可实现 AMR 的分布式筛查并改进抗生素处方
- 批准号:
MR/Y034481/1 - 财政年份:2024
- 资助金额:
$ 40万 - 项目类别:
Research Grant
CAREER: Green Functions as a Service: Towards Sustainable and Efficient Distributed Computing Infrastructure
职业:绿色功能即服务:迈向可持续、高效的分布式计算基础设施
- 批准号:
2340722 - 财政年份:2024
- 资助金额:
$ 40万 - 项目类别:
Continuing Grant