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

• 批准号: 2033671
• 负责人: Cong Shen
• 金额: $ 20万
• 依托单位: University of Virginia Main Campus
• 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
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2033671&HistoricalAwards=false
• 关键词: CCSS; Collaborative; Research; Towards; Resource

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.

联合学习（FL）是一种新兴的分布式机器学习范式，具有许多有吸引力的特性。尽管早期的研究表明了共同优化沟通和计算的潜力，但现有设计并不是针对FL的独特特征量身定制的。该项目旨在为无线FL开发一个新颖而严格的资源分配框架，我们将资源配给以随着时间的推移而强调平衡资源，以便明确捕获对最终学习结果的长期影响。资源配给建立在严格的理论基础上，并指导算法开发，该算法开发解决了物理和媒体访问控制（MAC）层中特定资源分配问题。 Federated Learning是一个新兴的无线通信应用程序，该项目有潜力推进这种新用例的技术开发。同时，理论基础，算法和验证将在机器学习，通信理论和无线网络中广泛推进最新技术。开发这种实用和有影响力的技术还将有助于维持美国在无线技术方面的领导，并保持管道以提供高质量，培训和创新的工程师。该项目从事协同活动，以成功设计和实施用于无线无线FL的资源侵害。在每个学习回合中，对FL的新型收敛分析进行了不同的资源，从而确立了一般的后期原理。在理论基础的指导下，该项目进一步建立了针对特定资源配给设计的全面算法框架，从物理层的位加载和自适应编码和调制到MAC层客户的选择，带宽分配以及权力控制。该奖项反映了NSF的法定任务，并通过评估构成了构成群体的范围，并反映了该奖项的范围。

项目成果

Federated Learning over Noisy Channels

• DOI: 10.1109/icc42927.2021.9500833
• 发表时间: 2021-01
• 期刊: ICC 2021 - IEEE International Conference on Communications
• 作者: Xizixiang Wei;Cong Shen

Federated Learning via Indirect Server-Client Communications

• DOI: 10.1109/ciss56502.2023.10089783
• 发表时间: 2023-02
• 期刊: 2023 57th Annual Conference on Information Sciences and Systems (CISS)
• 作者: Jieming Bian;Cong Shen;Jie Xu

FLORAS: Differentially Private Wireless Federated Learning Using Orthogonal Sequences

• DOI: 10.1109/icc45041.2023.10278611
• 发表时间: 2023-05
• 期刊: ICC 2023 - IEEE International Conference on Communications
• 作者: Xizixiang Wei;Tianhao Wang;Ruiquan Huang;Cong Shen;Jing Yang;H. Poor;Charles L. Brown

Federated Multi-armed Bandits with Personalization

• 发表时间: 2021-02
• 期刊: ArXiv
• 作者: Chengshuai Shi;Cong Shen;Jing Yang

Federated Multi-Armed Bandits

• DOI: 10.1609/aaai.v35i11.17156
• 发表时间: 2021-01
• 作者: Chengshuai Shi;Cong Shen