Jiawei Shao

News

  • [Mar. 2024] Our paper “FedCiR: Client-Invariant Representation Learning for Federated Non-IID Features” was accepted to IEEE Transactions on Mobile Computing. [Preprint]
  • [Feb. 2024] Our paper “Feature Matching Data Synthesis for Non-IID Federated Learning” was accepted to IEEE Transactions on Mobile Computing. [Paper]
  • [Dec. 2023] Our paper “Large language models empowered autonomous edge AI for connected intelligence” was accepted to IEEE Communications Magazine. [Paper]
  • [Nov. 2023] I am delighted to announce that I have successfully defended my PhD thesis. I would like to sincerely thank Prof. Jun Zhang, Prof. Khaled B. Letaief, Prof. Ross Murch, Prof. Qian Zhang, and Prof. Lin Dai for serving as examiners. Thanks also go to Prof. Hongyu Yu for serving as a chairperson of the examination committee.
  • [Nov. 2023] Our paper “Selective knowledge sharing for privacy-preserving federated distillation without a good teacher” was accepted to Nature Communications. [Paper]
  • [Nov. 2023] Our paper “Defending ChatGPT against Jailbreak attack via self-reminder” was accepted to Nature Machine Intelligence. [Paper]
  • [Nov. 2023] Our paper “Stochastic coded federated learning: Theoretical analysis and incentive mechanism design” was accepted to IEEE Transactions on Wireless Communications. [Paper]
  • [Nov. 2023] I received the HKTIIT Postgraduate Excellence Scholarships in the 2022-23 Academic Year.
  • [Sep. 2023] I presented a poster “EdgeGPT: GPT-empowered autonomous edge inference” on the IEEE Hong Kong 6G Wireless Summit. [Poster]
  • [Sep. 2023] Our paper “Task-oriented communication for edge video analytics” was accepted to IEEE Transactions on Wireless Communications. [Paper][Code]
  • [Jul. 2023] Manuscript “A survey of what to share in federated learning: Perspectives on model utility, privacy leakage, and communication efficiency” was submitted. [Preprint]
  • [Jun. 2023] I received the HKUST RedBird Academic Excellence Award in the 2022-23 Academic Year.
  • [Apr. 2023] Our paper “Low-complexity deep video compression with a distributed coding architecture” was accepted to ICME 2023. [Paper][Code]

Selected publications (Google Scholar Profile)

  • Edge intelligence, task-oriented communication:
    • J. Shao, X. Zhang, and J. Zhang, “Task-oriented communication for edge video analytics,” IEEE Trans. Wireless Commun., to appear. [Paper][Code]
    • J. Shao, Y. Mao, and J. Zhang, “Task-oriented communication for multi-device cooperative edge inference,” IEEE Trans. Wireless Commun., vol. 11, no. 1, pp. 73-87, Jan. 2023. [Paper][Code]
    • J. Shao, Y. Mao, and J. Zhang, “Learning task-oriented communication for edge inference: An information bottleneck approach,” IEEE J. Select. Areas Commun, vol. 40, no. 1, pp. 197-211, Jan. 2022. [Paper][Code]
    • J. Shao, J. Zhang, “Communication-computation trade-off in resource-constrained edge inference,” IEEE Commun. Mag., vol. 58, no. 12, pp. 20–26, Dec. 2020. [Paper][Code]
  • Federated learning:
    • J. Shao, F. Wu, and J. Zhang, “Selective knowledge sharing for privacy-preserving federated distillation without a good teacher,” Nature Communications, to appear. [Preprint][Code]
    • J. Shao, Y. Sun, S. Li, and J. Zhang, “DReS-FL: Dropout-resilient secure federated learning for non-IID clients via secret data sharing,” Thirty-sixth Conference on Neural Information Processing Systems (NeurIPS), New Orleans, LA, USA, Nov. 2022. [Paper]
  • Generative models and large language models:
    • Y. Shen, J. Shao, X. Zhang, Z. Lin, H. Pan, D. Li, J. Zhang, and K. Letaief, “Large language models empowered autonomous edge AI for connected intelligence,” IEEE Commun. Mag., to appear. [Preprint]
    • Y. Xie, J. Yi, J. Shao, J. Curl, L. Lyu, Q. Chen, X. Xie, F. Wu, “Defending ChatGPT against Jailbreak attack via self-reminder,” Nature Machine Intelligence, pp. 1-11, Dec. 2023. [Paper]

Submitted

  • J. Shao*, Z. Li*, W. Sun*, T. Zhou, Y. Sun, L. Liu, Z. Lin, and J. Zhang, “A Survey of What to Share in Federated Learning: perspectives on model utility, privacy leakage, and communication efficiency,” submitted. [Preprint] (*equal contribution with Zijian Li and Wenqiang Sun)