I am ✨ Xinbao Qiao (Sheen-bao Ciao /ʃɪnbaʊ/ /tʃjaʊ/), 🐼 Namesake of Panda Xinbao, a final-year master student in the Zhejiang University.
I graduated from Shandong University with a bachelor’s degree. Now I study at ZJUI with a master’s degree, advised by Meng Zhang.
My research interest focus on building data-centric ML systems that ensure trustworthy AI systems, and deploy these systems to solve real-world challenges, e.g., distributed systems and healthcare/biomedicine.
Publications
Hessian-Free Online Certified Unlearning
Xinbao Qiao, Meng Zhang, Ming Tang, Ermin Wei
- Approximate Machine Unlearning, Certified Data Removal, Privacy
TL;DR: addressing second-order certified unlearning gaps in non-convex settings and nonconvergence conditions, while achieving the most efficient data removal.
DynFrs: An Efficient Framework for Machine Unlearning in Random Forest
Shurong Wang, Zhuoyang Shen, Xinbao Qiao, Tongning Zhang, Meng Zhang
- Exact Machine Unlearning, Random Forest, Privacy
TL;DR: combining subsampling methods, the lazy tag strategy, and the robustness of Extremely Randomized Trees to achieve Random Forest unlearning in dynamic environments.
Soft Weighted Machine Unlearning
Xinbao Qiao, Ningning Ding, Yushi Cheng, Meng Zhang
- Machine Unlearning, Influence Function, Fairness, Robustness
TL;DR: Addressing the challenge of excessive unlearning in non-privacy-focused scenarios through soft-weighted strategies.
Educations
- 2022.09 - 2025.06, Master, Artificial Intelligence, Zhejiang University
- 2018.09 - 2022.07, Bachelor, Communication Engineering, Shandong Univeristy.