DENOS Lab, University of Calgary ← Back to team
Yunkai Bao

Yunkai Bao

PhD Student in Electrical and Software Engineering, University of Calgary

Federated Learning

Google Scholar

Biography

Yunkai Bao is a PhD student at DENOS Lab working on machine learning, federated learning, IoT, and agentic AI. His research centres on training under real client constraints, including availability budgets and energy limits, and extends to privacy-preserving federated analysis of multicentre clinical trial data.

Projects

  • Federated learning under client budgets

    Client selection and semi-decentralized training that respect device availability and energy budgets instead of assuming clients are always reachable.

  • Privacy-preserving trial analysis

    Federated analysis that reproduces non-inferiority results from the AcT multicentre stroke trial without pooling patient data.

Publications

  • IEEE BigData2024

    Energy-efficient Federated Learning with Dynamic Model Size Allocation

    M. S. C. Kumar, Yunkai Bao, Xin Wang, and Steve Drew

  • IEEE GLOBECOM2023

    Federated Learning with Client Availability Budgets

    Yunkai Bao, Steve Drew, Xin Wang, Jiayu Zhou, and Xiaoguang Niu

  • IEEE INFOCOM-W2025

    Semi-decentralized Federated Time Series Prediction with Client Availability Budgets

    Yunkai Bao, R. Safarzadeh, Xin Wang, and Steve Drew

  • SSRN

    Privacy-Preserving Federated Analysis Reproduces Non-Inferiority Results from the AcT Multicentre Stroke Trial

    Yunkai Bao, Zainab Saad, K. Duarte, Farhan Abbas, T. Sajobi, Jessalyn K. Holodinsky, Bijoy K. Menon, et al.

Achievements

  • Third place in data visualization at the CANIS Hackathon hosted by Schulich Ignite, with Leo Wei and Jiajun Wu.

← All team members