Project Summary

Recent emerging federated learning (FL) allows distributed data sources to collaboratively train a global model without sharing their privacy sensitive raw data. However, due to the huge size of the deep learning model, the model downloads and updates generate significant amount of network traffic which exerts tremendous burden to existing telecommunication infrastructure. This project takes FL over 5G mobile devices as a workable application scenario to address this dilemma, which will significantly improve the design, analysis and implementation of FL over 5G mobile devices. The research outcomes will substantially enrich the knowledge of machine learning technologies and 5G systems and beyond. Moreover, this project is multidisciplinary, involving machine learning/deep learning/federated learning, edge computing, wireless communications and networking, security and privacy, computer architectural design, etc., which will serve as a fruitful training ground for both graduate and undergraduate students to equip them with multidisciplinary skills for future work force to boost the national economy. Furthermore, outreach activities to high school students will increase the participation of female and minority students in science and engineering.

Specifically, by observing that iterative model updates tend to show high sparsity, the investigators leverage model update sparsity to design model pruning and quantization schemes to optimize local training and privacy-preserving model updating in order to lower both energy consumption and model update traffic. They achieve this design goal by conducting the four research tasks: (1) designing software-hardware co-designed model pruning schemes and adaptive quantization techniques in FL within a single 5G mobile device according to the local data and model sparsity property to reduce the local computation and memory access; (2) making sound trade-off between "working" (i.e., local computing) and "talking" (i.e., 5G wireless transmissions) to boost the overall energy/communications efficiency for FL over 5G mobile devices; (3) developing novel differentially private compression schemes based on sparsification property and quantization adaptability to rigorously protect data privacy while maintaining high model accuracy and communication efficiency in FL; and (4) building a testbed to thoroughly evaluate the proposed designs.

Personnel

Principal Investigators

• Miao Pan (leading PI) and Xin Fu (Co-PI), University of Houston
  
• Yuguang Fang (PI), University of Florida
  
• Yuanxiong Guo (PI) and Yanmin Gong (Co-PI), University of Texas, San Antonio
  

Graduate Students (at UF)

• Xianhao Chen, University of Florida, Ph.D student (10/2021-05/2022), who will be an Assistant Professor with the Department of Electrical and Electronic Engineering at University of Hong Kong, Hong Kong, China.
• Guangyu Zhu, University of Florida, Ph.D student (10/2021-present)

Publications

Copyright Notice

Papers downloadable on this page are under copyright protection. Please read and conform to all applicable copyright laws. Most downloadable papers are in PDF format, which can be viewed by PDF reader freely available from Adobe. Your comments are always welcome, please drop me a line at fang@ece.ufl.edu

Papers in Refereed Journals or Magazines

1. J. Li, L. Zhang, K. Xue, Y. Fang and Q. Sun, "Secure transmission by leveraging multiple intelligent reflecting surfaces in MISO Systems,'' Accepted for publication in IEEE Transactions on Mobile Computing. DOI: 10.1109/TMC.2021.3114167.
2. D. Shi, L. Li, R. Chen, P. Prakash, M. Pan and Y. Fang, "Towards energy efficient federated learning over 5G+ mobile devices,'' Accepted for publication in IEEE Wireless Communications.
3. Y. Deng, X. Chen, G. Zhu, Y. Fang, Z. Chen and X. Deng, "Actions at the edge: Jointly optimizing the resources in multi-access edge computing,'' IEEE Wireless Communications, vol.29, no.2, pp.192-198, April 2022.
4. X. Chen, Y. Ding, G. Zhu, D. Wang and Y. Fang, "From resource auction to service auction: An auction paradigm shift in wireless networks,'' IEEE Wireless Communications, vol.29, no.2, pp.185-191, April 2022.
5. X. Chen, G. Zhu, H. Ding, L. Zhang, H. Zhang and Y. Fang, "End-to-end service auction: A general double auction mechanism for edge computing services,'' Accepted for publications in IEEE/ACM Transactions on Networking.
6. X. Chen, G. Zhu and Y. Fang, "Federated learning over multi-hop wireless networks with in-network aggregation,'' Accepted for publication in IEEE Transactions on Wireless Communications. DOI: 10.1109/TWC.2022.3168538.

Papers in Refereed Conferences

Outreach and Education Activities for Broader Impact

Course Development

Student Mentoring

Research Dissemination

Talks/Seminars

1. Y. Fang, "Vehicles as a Service (VaaS): How to Leverage Vehicles to Beef Up the Edge,'' Invited Talk, Zhejiang University Overseas Academicians Workshop, Zhejiang University, Hangzhou, China, March 9-13, 2022. (Held Virtually).
2. Y. Fang, "Vehicles as a Service (VaaS): How to Leverage Vehicles to Beef Up the Edge,'' Invited Talk, The 3rd International Workshop on Internet of Vehicles and Edge Computing, Shanghai Jiao Tong University, Shanghai, China, January 22-23, 2022. (Held Virtually).
3. Y. Fang, "Beef Up the Edge: Building a Service Network for Sensing, Communications, Computing, Storage and Intelligence at the Edge,'' Keynote, The 23rd IEEE International Conferences on High Performance Computing and Communications (HPCC), Hyper-Intelligence Congress 2021, December 20-22, Haikou, Hainan, China (Held online due to pandemic).

You are the visitor since July 22, 1999.