NSF CAREER: Ubiquitous & Time-Critical Federated Learning via Cooperative Mobile Edge Networking

Award: NSF CNS-2047761
Period: Oct 1, 2021 – Sep 30, 2027

Project Overview

We develop a federated learning (FL) framework leveraging cooperative mobile edge networking to support distributed IoT data with high accuracy, low latency, and rigorous privacy guarantees. The project advances:

  • Network-aware learning algorithms: Two-level, topology- and channel-aware FL to efficiently train from decentralized on-device data over wireless edge networks.
  • Joint optimization of learning & resources: Deep RL–driven client scheduling and resource allocation to achieve rapid, robust convergence under device/network heterogeneity and constraints.
  • Privacy & robustness: Differential privacy and attack-resilient methods that protect personal data while maintaining model utility and reducing communication overhead.

These advances bridge wireless networking and modern ML to enable next-generation edge AI systems powering delay-sensitive, data-driven IoT applications.

CAREER project concept: cooperative mobile edge networking for federated learning Prototype/testbed for federated edge learning

People

  • PI: Yanmin Gong
  • Students: Zhidong Gao (PhD, graduated), Zhenxiao Zhang (PhD, graduated), Yu Zhang (PhD, graduated), Rui Hu (PhD, graduated), Xiangxing Guo (PhD), Guohao Yang (Research Assistant)

Selected Publications (2025–2026)

  • FedKRSO: Communication and Memory Efficient Federated Fine-Tuning of Large Language Models G. Yang, T. Wu, Y. Guo, Y. Sun, Y. Gong. IEEE INFOCOM, 2026

  • PFedSAM: Secure Federated Learning Against Backdoor Attacks via Personalized Sharpness-Aware Minimization
    Z. Zhang, Y. Guo, Y. Gong. IEEE ICC, 2025.

  • Federated Adaptive Fine-Tuning of Large Language Models with Heterogeneous Quantization and LoRA
    Z. Gao, Z. Zhang, Y. Gong, Y. Guo. IEEE INFOCOM, 2025. (Acceptance ratio: 18.65%)

  • Online Client Scheduling and Resource Allocation for Efficient Federated Edge Learning
    Y. Zhang, Z. Gao, Z. Zhang, T. Wang, Y. Gong, Y. Guo. IEEE Trans. Vehicular Technology (TVT), 2025.

Earlier Representative Publications

  • Heterogeneity-Aware Cooperative Federated Edge Learning with Adaptive Computation and Communication Compression
    Z. Zhang, Z. Gao, Y. Guo, Y. Gong. IEEE Trans. Mobile Computing (TMC), 2024.
  • REWAFL: Residual Energy and Wireless Aware Participant Selection for Efficient Federated Learning over Mobile Devices
    Y. Li, X. Qin, J. Geng, R. Chen, Y. Hou, Y. Gong, M. Pan, P. Zhang. IEEE TMC, 2024.
  • Hybrid Local SGD for Federated Learning with Heterogeneous Communications
    Y. Guo, Y. Sun, R. Hu, Y. Gong. ICLR, 2022.
  • Concentrated Differentially Private Federated Learning with Performance Analysis
    R. Hu, Y. Guo, Y. Gong. IEEE Open Journal of the Computer Society, 2021.
  • Energy-Efficient Distributed ML at the Wireless Edge with Device-to-Device Communication
    R. Hu, Y. Guo, Y. Gong. IEEE ICC, 2022.
  • Scalable and Low-Latency Federated Learning with Cooperative Mobile Edge Networking
    Z. Zhang, Z. Gao, Y. Guo, Y. Gong. IEEE TMC, in press/early access.

News & Updates

  • 2026: INFOCOM’26 accepted paper on efficient federated fine-tuning for LLMs.
  • 2025: INFOCOM’25 accepted paper on federated adaptive fine-tuning for LLMs.
  • 2025: ICC’25 accepted paper (PFedSAM) on secure FL against backdoor attacks.
  • 2024–2025: Multiple journal publications in TMC, TVT, IoT-J, and TNSE.

Contact

  • Email: yanmin.gong@tamu.edu
  • GitHub: @yanmingong · Google Scholar · ORCID