Fan Wu |
Email / Google Scholar / GitHub / LinkedIn / CV |
“Dwell on the beauty of life. Watch the stars, and see yourself running with them.” -- Marcus Aurelius
|
This is kkkkahlua, a 2nd year CS PhD student at University of Illinois at Urbana-Champaign, advised by Prof. Bo Li. Before that, I graduated with a B.S. degree in Computer Science from Nanjing University with distinction. My current research interests lie in machine learning, reinforcement learning, privacy preservation, and data valuation. I am a cofounder of NJU-CSE-Flyers Global Alumni Network. |
|
Publications
LinkTeller: Recovering Private Edges from Graph Neural Networks via Influence Analysis
Fan Wu, Yunhui Long, Ce Zhang, Bo Li
S&P 2022
DataLens: Scalable Privacy Preserving Training via Gradient Compression and Aggregation
Boxin Wang*, Fan Wu*, Yunhui Long*, Luka Rimanic, Ce Zhang, Bo Li
CCS 2021
Scalability vs. Utility: Do We Have to Sacrifice One for the Other in Data Importance Quantification?
Ruoxi Jia, Fan Wu*, Xuehui Sun*, Jiacen Xu*, David Dao, Bhavya Kailkhura, Ce Zhang, Bo Li, Dawn Song
CVPR 2021
The Twelvefold Way of Non-Sequential Lossless Compression
Illinois Information Theory Students (one of), Sourya Basu, Lav R. Varshney
Data Compression Conference 2021 (poster)
DeGNN: Improving Graph Neural Networks with Graph Decomposition
(20 authors) Xupeng Miao, Nezihe Merve Gürel, Wentao Zhang, ..., Fan Wu, ..., Bin Cui, Ce Zhang
KDD 2021
Factor Graph Neural Network
Zhen Zhang, Fan Wu, Wee Sun Lee
NeurIPS 2020
* indicates equal contribution