Fei Wang

Ph.D. Student @ ECE - UofT

Journal papers

  • Fei Wang, Baochun Li, “Data Reconstruction and Protection in Federated Learning for Fine-Tuning Large Language Models,” in IEEE Transactions on Big Data, Special Section on Pre-Trained Large Language Models, 2024 (JIF: 7.2). [Paper]

  • Fei Wang, Ethan Hugh, Baochun Li, “More than Enough is Too Much: Adaptive Defenses against Gradient Leakage in Production Federated Learning,” in IEEE/ACM Transactions on Networking, 2024 (JIF: 3.7). [Paper]

  • Fei Wang, Baochun Li, “Harnessing the Power of Local Supervision in Federated Learning,” in IEEE Transactions on Big Data, Special Issue on Federated Learning for Big Data Applications, 2024 (JIF: 7.2). [Paper]

  • Fei Wang, Baochun Li, Bo Li, “Federated Unlearning and Its Privacy Threats,” in IEEE Network, 2023 (JIF: 10.294). [Paper]

  • Fei Wang, Baochun Li, Bo Li, “Quality-Oriented Federated Learning on the Fly,” in IEEE Network, Special Issue on Federated Optimizations and Networked Edge Intelligence, vol. 36, no. 5, pp. 152–159, September–October 2022 (JIF: 10.294). [Paper]

  • Salma Emara, Fei Wang, Baochun Li, Timothy Zeyl, “Pareto: Fair Congestion Control with Online Reinforcement Learning,” in IEEE Transactions on Network Science and Engineering, vol. 9, no. 5, pp. 3731–3748, September–October 2022 (JIF: 5.033). [Paper]

Conference papers

  • Salma Emara, Daniel Liu, Fei Wang, Baochun Li, “Cascade: Enhancing Reinforcement Learning with Curriculum Federated Learning and Interference Avoidance — A Case Study in Adaptive Bitrate Selection,” in the Proceedings of IEEE INFOCOM 2024 Workshop on Distributed Machine Learning and Fog Networks (FOGML), Vancouver, Canada, May 20-23, 2024. [Paper]

  • Baochun Li, Ningxin Su, Chen Ying, Fei Wang. “Plato: An Open-Source Research Framework for Production Federated Learning,” in the Proceedings of ACM Turing Award Celebration Conference (TURC), Wuhan, China, July 28–30, 2023. [Paper]

  • Fei Wang, Salma Emara, Isidor Kaplan, Baochun Li, Timothy Zeyl, “Multi-Agent Deep Reinforcement Learning for Cooperative Edge Caching via Hybrid Communication,” in the Proceedings of IEEE ICC 2023, Selected Areas in Communications — Machine Learning for Communications and Networking Track, Rome, Italy, May 28 – June 1, 2023. [Paper] [Slides]

  • Fei Wang, Ethan Hugh, Baochun Li, “More than Enough is Too Much: Adaptive Defenses against Gradient Leakage in Production Federated Learning,” in the Proceedings of IEEE INFOCOM 2023, New York Area, U.S.A., May 17–20, 2023 (acceptance rate: 19.2%, Best Paper Award). [Paper] [Code] [Slides]

  • Salma Emara, Fei Wang, Isidor Kaplan, Baochun Li, “Ivory: Learning Network Adaptive Streaming Codes,” in the Proceedings of the 30th IEEE/ACM International Symposium on Quality of Service (IWQoS), Online, June 10–12, 2022 (acceptance rate: 24.3%). [Paper]

US patents