Scholar
Hao Zheng
Google Scholar ID: NBIwpN8AAAAJ
Central South University, Western University
Citations & Impact
Citations
128
H-index
6
i10-index
4
Publications
19
Co-authors
4
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Published multiple papers, including:
- - “Versatile Transferable Unlearnable Example Generator” accepted at NeurIPS 2025.
- - “Proactive Spatio-Temporal Request Prediction for Replica Placement in Edge-Cloud Computing” accepted at IoTJ.
- - “ElimPCL: Eliminating Noise Accumulation with Progressive Curriculum Labeling for Source-Free Domain Adaptation” and “PCM-SAR: Physics-Driven Contrastive Mutual Learning for SAR Classification” accepted at ICME 2025.
- - “FedCALM: Conflict-aware Layer-wise Mitigation for Selective Aggregation in Deeper Personalized Federated Learning” accepted at CVPR 2025.
- - “ConFREE: Conflict-free Client Update Aggregation for Personalized Federated Learning” accepted at AAAI 2025 (oral, acceptance rate ≈ 4.6%).
- - “GradPFL: Gradient-Driven Adaptive Clustering in Personalized Federated Learning” accepted at ICASSP 2025.
- Also served as a reviewer for several top conferences, such as AAAI 25-26, MM 2025, ICLR 24-26, NeurIPS 24-25, etc.
Research Experience
- Currently pursuing a Ph.D. at the School of Computer Science and Engineering, Central South University, and serving as a visiting researcher at Western University.
Education
- Bachelor's degree from Taiyuan University of Technology in 2018; Master's degree from Central South University in 2021; currently a fourth-year Ph.D. student at Central South University.
Background
- Research interests include Optimization for Personalized Federated Learning and Deep Learning & Computer Vision in Remote Sensing. Currently a Ph.D. student at the School of Computer Science and Engineering, Central South University, supervised by Prof. Zhigang Hu. Also a visiting researcher at Western University, working under the guidance of Prof. Boyu Wang and Prof. Charles Ling.
Miscellany
- Currently looking for postdoctoral opportunities to continue exploring exciting problems in machine learning.
