About
I am a Post-doctoral Fellow in the Department of Mathematics at The University of Hong Kong, advised by Prof. Zhiwen Zhang.
Prior to this, I received my B.S. degree and Ph.D. degree from the Department of Mathematical Sciences at Tsinghua University. My Ph.D. advisor was Prof. Zuoqiang Shi.
My current research focuses on semi-supervised learning, PDE-based methods on graphs and PDE-inspired neural networks.
Selected Publications
View All →Interface Laplace Learning: Learnable Interface Term Helps Semi-Supervised Learning
Tangjun Wang, Chenglong Bao, Zuoqiang Shi
CSIAM Transactions on Applied Mathematics (to appear)
An improvement over Laplace learning that explicitly models the interface between different classes, significantly improving performance under extremely low label rates.
Convection-Diffusion Equation: A Theoretically Certified Framework for Neural Networks
Tangjun Wang, Chenglong Bao, Zuoqiang Shi
IEEE Transactions on Pattern Analysis and Machine Intelligence
An axiomatic framework that bridges neural networks and PDEs via a convection–diffusion formulation, together with a novel PDE-inspired network architecture (COIN).
Diffusion Mechanism in Residual Neural Network: Theory and Applications
Tangjun Wang, Zehao Dou, Chenglong Bao, Zuoqiang Shi
IEEE Transactions on Pattern Analysis and Machine Intelligence
A diffusion-enhanced residual neural network (Diff-ResNet) inspired by convection–diffusion ODEs, with theoretical guarantees on improving class separability.
News
I receive my Ph.D. degree from Tsinghua University 🎉