Scholar
Shengkun Zhu
Google Scholar ID: 7c39MpIAAAAJ
Wuhan University
Citations & Impact
Citations
11
H-index
2
i10-index
0
Publications
7
Co-authors
5
list available
Contact
Publications
Resume (English only)
Academic Achievements
- SIGMOD 2024: F3KM: Federated, Fair, and Fast k-means (First author)
- KDD 2025: FedAPM: Federated Learning via ADMM with Partial Model Personalization (First author)
- VLDB 2026: Highly-Efficient Large-Scale k-means with Individual Fairness (First author)
- VLDB 2025: Federated and Balanced Clustering for High-dimensional Data (Co-first author)
- Serves as a reviewer for JMLR and IEEE TKDE
- National Scholarship, Wuhan University, 2023
- DiDi Scholarship Second Prize, Wuhan University, 2024
- DiDi Scholarship Third Prize, Wuhan University, 2025
Background
- Ph.D. student at School of Computer Science, Wuhan University. Research interests include optimization theory, large language model training & fine-tuning, federated learning, and clustering algorithms.
- Focuses on convex and non-convex optimization algorithms and their convergence analysis, with applications in machine learning and deep learning.
- Studies efficient training methods for large language models and parameter-efficient fine-tuning techniques.
- Explores privacy-preserving distributed machine learning, federated optimization algorithms, and communication-efficient training strategies in heterogeneous environments.
- Develops advanced clustering methods (e.g., spectral clustering) for large-scale data analysis.
