CAREER: Strengthening the Theoretical Foundations of Federated Learning: Utilizing Underlying Data Statistics in Mitigating Heterogeneity and Client Faults

职业:加强联邦学习的理论基础:利用底层数据统计来减轻异构性和客户端故障

基本信息

  • 批准号:
    2340482
  • 负责人:
  • 金额:
    $ 61.05万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Continuing Grant
  • 财政年份:
    2024
  • 资助国家:
    美国
  • 起止时间:
    2024-01-15 至 2028-12-31
  • 项目状态:
    未结题

项目摘要

Real-world applications that would benefit from improved machine learning encompass a wide range of industries and domains such as healthcare, autonomous vehicles, natural language processing, and manufacturing and industry. Distributed machine learning has gained significant momentum in recent years due to the increasing need for real-time data processing, low latency, and privacy concerns. The rapid development of edge devices broadens the applicability of distributed machine learning yet brings nontrivial challenges that call for revisiting the fundamental principles and algorithm designs for federated learning. The research goal of this project is to consolidate the theoretical foundations and to enrich the algorithmic toolbox of distributed machine learning with a focus on enhancing its resilience against a wide range of data heterogeneity, system imperfection (or faults), and external attacks. The educational objective of this project is to promote the importance of principled mathematical thinking for solving real-world problems in machine learning among the next generation of machine learning practitioners and researchers, with a focus on developing programs that target women and underrepresented minority groups. Federated learning is a rapidly evolving distributed machine learning approach that facilitates global model training without the necessity of sharing raw local data. Most existing theoretical analysis of federated learning is derived from an optimization perspective but the underlying statistical structure of the dataset is mostly overlooked. This often leads to misalignment between the pessimistic theoretical predictions and empirical success. In addition, recent work suggests that the bounded gradient dissimilarity conditions, which are frequently adopted in federated learning analysis, may be too pessimistic for practical applications. Motivated by our preliminary successes and backed by extensive prior work, this proposal aims to strengthen the theoretical foundations of federated learning and to enhance its resilience against a wide range of data heterogeneity and system failures, by leveraging the underlying structures of the federated datasets and by designing new algorithms. Towards this goal we will employ and innovate tools from statistical learning, distributed computing, high-dimensional probabilities, and optimization.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.
从改进的机器学习中受益的实际应用包括广泛的行业和领域,如医疗保健,自动驾驶汽车,自然语言处理以及制造业和工业。近年来,由于对实时数据处理、低延迟和隐私问题的需求日益增加,分布式机器学习获得了巨大的发展势头。边缘设备的快速发展拓宽了分布式机器学习的适用性,但也带来了重大挑战,需要重新审视联邦学习的基本原理和算法设计。该项目的研究目标是巩固分布式机器学习的理论基础,丰富分布式机器学习的算法工具箱,重点是增强其对各种数据异构性,系统缺陷(或故障)和外部攻击的弹性。该项目的教育目标是在下一代机器学习从业者和研究人员中推广有原则的数学思维对于解决机器学习中的现实问题的重要性,重点是开发针对女性和代表性不足的少数群体的项目。 联邦学习是一种快速发展的分布式机器学习方法,它可以促进全局模型训练,而无需共享原始本地数据。大多数现有的联邦学习理论分析都是从优化的角度出发的,但数据集的底层统计结构大多被忽视了。这往往导致悲观的理论预测和经验成功之间的不一致。此外,最近的工作表明,联邦学习分析中经常采用的有界梯度相异度条件可能对实际应用过于悲观。在我们初步成功的推动下,并在大量先前工作的支持下,该提案旨在加强联邦学习的理论基础,并通过利用联邦数据集的底层结构和设计新算法,增强其对各种数据异构性和系统故障的弹性。为了实现这一目标,我们将采用和创新的工具,从统计学习,分布式计算,高维概率和优化。这个奖项反映了NSF的法定使命,并已被认为是值得的支持,通过评估使用基金会的智力价值和更广泛的影响审查标准。

项目成果

期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)

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

{{ 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 }}

Lili Su其他文献

Non-Bayesian Learning in the Presence of Byzantine Agents
拜占庭代理存在下的非贝叶斯学习
Highly potent and selective 4,4'‐biphenyl‐4‐acylate‐4'‐N‐n‐butylcarbamate inhibitors of Pseudomonas species lipase
假单胞菌属脂肪酶的高效选择性 4,4-联苯-4-酰化物-4-N-正丁基氨基甲酸酯抑制剂
  • DOI:
  • 发表时间:
    2005
  • 期刊:
  • 影响因子:
    0
  • 作者:
    G. Lin;Gan;Yan;Lili Su;Pei
  • 通讯作者:
    Pei
Semantic-oriented Ubiquitous Learning object model
面向语义的普适学习对象模型
A visual tracking algorithm based on context constraint and aberration suppression
一种基于上下文约束和像差抑制的视觉跟踪算法
  • DOI:
    10.1016/j.knosys.2025.113658
  • 发表时间:
    2025-09-05
  • 期刊:
  • 影响因子:
    7.600
  • 作者:
    Yinqiang Su;Lili Su;Fang Xu;Hui Zhao
  • 通讯作者:
    Hui Zhao
Toxic Effects and Mechanism of 2,2',4,4'-Tetrabromodiphenyl Ether
2,2,4,4-四溴二苯醚的毒性作用及机制
  • DOI:
  • 发表时间:
    2016
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Lili Su;Weina Sun;Xizhu Yan
  • 通讯作者:
    Xizhu Yan

Lili Su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 }}

相似海外基金

CC* Planning: Strengthening Central Michigan University's Cyberinfrastructure
CC* 规划:加强中央密歇根大学的网络基础设施
  • 批准号:
    2345749
  • 财政年份:
    2024
  • 资助金额:
    $ 61.05万
  • 项目类别:
    Standard Grant
ART: Translational Research Ambassadors Network for Strengthening Institutional Capacity and Fostering a Responsive and Open Mindset (TRANSFORM)
ART:加强机构能力和培养积极响应和开放心态的转化研究大使网络(TRANSFORM)
  • 批准号:
    2331208
  • 财政年份:
    2024
  • 资助金额:
    $ 61.05万
  • 项目类别:
    Cooperative Agreement
Collaborative Research: Design: Strengthening Inclusion by Change in Building Equity, Diversity and Understanding (SICBEDU) in Integrative Biology
合作研究:设计:通过改变综合生物学中的公平、多样性和理解(SICBEDU)来加强包容性
  • 批准号:
    2335235
  • 财政年份:
    2024
  • 资助金额:
    $ 61.05万
  • 项目类别:
    Standard Grant
Applying a Program Science approach for strengthening partnerships and advancing embedded research to optimize public health programming for HIV and sexually transmitted and blood-borne infections among criminalized populations in the Global South
应用计划科学方法来加强伙伴关系并推进嵌入式研究,以优化南半球犯罪人群中针对艾滋病毒、性传播和血源性感染的公共卫生规划
  • 批准号:
    502554
  • 财政年份:
    2024
  • 资助金额:
    $ 61.05万
  • 项目类别:
Baycrest Academy for Research and Education Summer Program in Aging (SPA): Strengthening research competencies, cultivating empathy, building interprofessional networks and skills, and fostering innovation among the next generation of healthcare workers t
Baycrest Academy for Research and Education Summer Program in Aging (SPA):加强研究能力,培养同理心,建立跨专业网络和技能,并促进下一代医疗保健工作者的创新
  • 批准号:
    498310
  • 财政年份:
    2024
  • 资助金额:
    $ 61.05万
  • 项目类别:
    Operating Grants
Strengthening Evidence-Based Policy Practice for Sustainable Food Systems under the EU-AU Partnership
在欧盟-非盟伙伴关系下加强可持续粮食系统的循证政策实践
  • 批准号:
    10101252
  • 财政年份:
    2024
  • 资助金额:
    $ 61.05万
  • 项目类别:
    EU-Funded
Seismic Performance Evaluation and Sustainable Strengthening of Unreinforced Masonry Infill Walls
无筋砌体填充墙的抗震性能评价与可持续加固
  • 批准号:
    24K17338
  • 财政年份:
    2024
  • 资助金额:
    $ 61.05万
  • 项目类别:
    Grant-in-Aid for Early-Career Scientists
Strengthening the Mathematics and Science Teacher Pathways in the Post-Pandemic Environment
加强大流行后环境中的数学和科学教师的途径
  • 批准号:
    2344918
  • 财政年份:
    2024
  • 资助金额:
    $ 61.05万
  • 项目类别:
    Continuing Grant
Collaborative Research: Improving Upper Division Physics Education and Strengthening Student Research Opportunities at 14 HSIs in California
合作研究:改善加州 14 所 HSI 的高年级物理教育并加强学生研究机会
  • 批准号:
    2345092
  • 财政年份:
    2024
  • 资助金额:
    $ 61.05万
  • 项目类别:
    Standard Grant
Ravens Strengthening STEM Education Pathways
乌鸦加强 STEM 教育途径
  • 批准号:
    2345150
  • 财政年份:
    2024
  • 资助金额:
    $ 61.05万
  • 项目类别:
    Standard Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了