Jun Zhang

PhD, FIEEE
alt text 

Associate Professor, IEEE Fellow
Department of Electronic and Computer Engineering (ECE)
Computer Engineering Program (CPEG)
The Hong Kong University of Science and Technology (HKUST)

Distinguished Lecturer, IEEE Communications Society

Office: Room 2430
Email: eejzhang@ust.hk
Phone: +852 2358-7050
Google Scholar Citation

Openings

  • I am recruiting PhD students for Fall 2024, on the following topics:

    • Edge AI (multi-modal data compression and analytics, edge-assisted robots)

    • Cooperative AI (cooperative perception, multi-agent reinforcement learning)

    • AI safety, trustworthy (privacy-preserving inference and learning)

  • There are multiple openings of research assistant professor/postdocs/RAs/engineers, in communication system prototyping (high priority), deep learning for wireless communication, federated learning, and edge AI. If you are interested, feel free to contact me.

What's new

  • (New Paper) “Selective knowledge sharing for privacy-preserving federated distillation without a good teacher,” submitted. [Paper]

  • (ICME 23) “Low-complexity deep video compression with a distributed coding architecture,” accepted by ICME 2023. [Paper] [GitHub]

  • (CVPR 23) “Generalized relation modeling for transformer tracking”, accepted by CVPR 2023. [Paper] [GitHub]

  • (ICLR 23) Two papers accepted to ICLR 2023.

    • “Sparse Mixture-of-Experts are Domain Generalizable Learners” (notable-top-5%, oral) [Paper] [GitHub]

    • “LDMIC: Learning-based distributed multi-view image coding” [Paper] [GitHub]

  • (AAMAS 23) “AC2C: Adaptively controlled two-hop communication for multi-agent reinforcement learning,” accepted by AAMAS 2023. [Paper]

  • (NeurIPS 22) “DReS-FL: Dropout-resilient secure federated learning for non-IID clients via secret data sharing,” accepted by NeurIPS 2022. [Paper]

  • (New Paper) “Task-oriented communication for edge video analytics,” submitted. [Paper]

Research Interests

  • Edge AI and Edge Computing

    • Edge video analytics; deep image/video compression; cooperative perception

  • Cooperative AI

    • Privacy-preserving collaborative learning; multi-agent reinforcement learning

  • Wireless Communications and Networking

    • Machine learning for wireless communications; wireless sensing

Selected Publications

  • Edge AI and Edge Computing

    • X. Zhang, J. Shao, and J. Zhang, “Low-complexity deep video compression with a distributed coding architecture,” IEEE International Conference on Multimedia and Expo (ICME), Brisbane, Australia, July 2023. [Paper] [GitHub]

    • S. Gao, C. Zhou, and J. Zhang, “Generalized relation modeling for transformer tracking,” IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, Canada, Jun. 2023. [Paper] [GitHub]

    • X. Zhang, J. Shao, and J. Zhang, “LDMIC: Learning-based distributed multi-view image coding,” International Conference on Learning Representations (ICLR), Kigali, Rwanda, May 2023. [Paper] [GitHub]

    • J. Shao, X. Zhang, and J. Zhang, “Task-oriented communication for edge video analytics,” submitted. [Paper]

    • 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] [GitHub]

    • J. Zhang and K. B. Letaief, “Mobile edge intelligence and computing for the Internet of vehicles,” Proc. IEEE, vol. 108, no. 2, pp. 246–261, Feb. 2020. [Paper]

  • Federated Learning, Safe/Robust AI

    • J. Shao, F. Wu, and J. Zhang, “Selective knowledge sharing for privacy-preserving federated distillation without a good teacher,” submitted. [Paper]

    • B. Li*, Y. Shen*, J. Yang, Y. Wang, J. Ren, T. Che, J. Zhang, and Z. Liu, “Sparse Mixture-of-Experts are Domain Generalizable Learners,” International Conference on Learning Representations (ICLR), Kigali, Rwanda, May 2023. (Oral presentation) [Paper] [GitHub]

    • W. Sun, S. Li, Y. Sun, and J. Zhang, “DABS: Data-agnostic backdoor attack at the server in federated learning,” Backdoor Attacks and Defenses in Machine Learning (BANDS) Workshop at ICLR 2023, Kigali, Rwanda, May 2023. (Spotlight presentation) [Paper]

    • T. Zhou, J. Zhang, and D. Tsang, “FedFA: Federated learning with feature anchors to align feature and classifier for heterogeneous data,” submitted. [Paper]

    • J. Shao, Y. Sun, S. Li, and J. Zhang, “DReS-FL: Dropout-resilient secure federated learning for non-IID clients via secret data sharing,” NeurIPS 2022. [Paper] (Acceptance Rate: 25.6%)

  • Wireless Communications

    • W. Yu, Y. Shen, H. He, X. Yu, S.H. Song, J. Zhang, and K. B. Letaief, “An adaptive and robust deep learning framework for THz ultra-massive MIMO channel estimation,” IEEE J. Sel. Topics Signal Process., to appear. [Paper] [GitHub]

    • Y. Shen, J. Zhang, S.H. Song, and K. B. Letaief, “Graph neural networks for wireless communications: From theory to practice,” IEEE Trans. Wireless Commun., vol. 22, no. 5, pp. 3554-3569, May 2023. [Paper] [GitHub]

    • Y. Shen, Y. Shi, J. Zhang, and K. B. Letaief, “Graph neural networks for scalable radio resource management: architecture design and theoretical analysis,” IEEE J. Select. Areas Commun, vol. 39, no. 1, pp. 101–115, Jan. 2021. [Paper]