Name: Fangchen Yu
Type: User
Company: The Chinese University of Hong Kong, Shenzhen
Bio: Fangchen Yu is a Ph.D. candidate from The Chinese University of Hong Kong, Shenzhen (CUHK-SZ). His research interests are in statistical machine learning.
Fangchen Yu's Projects
This project extends the idea of the innovative architecture of Kolmogorov-Arnold Networks (KAN) to the Convolutional Layers, changing the classic linear transformation of the convolution to learnable non linear activations in each pixel.
DocReal: Robust Document Dewarping of Real-Life Images via Attention-Enhanced Control Point Prediction
The source code for the ECAI'2023 paper titled "Highly-Efficient Robinson-Foulds Distance Estimation with Matrix Correction".
The source code for the AAAI'2024 paper titled "FedLF: Layer-Wise Fair Federated Learning".
The source code for the AAAI'2023 paper titled "Metric Nearness Made Practical".
The source code for the UAI'2023 paper titled "Online Estimation of Similarity Matrices with Incomplete Data".
AcadHomepage: A Modern and Responsive Academic Personal Homepage
The source code for the NeurIPS'2023 paper titled "Boosting Spectral Clustering on Incomplete Data via Kernel Correction and Affinity Learning".