activity
20222026
most citedPermutation Equivariant Graph Framelets for Heterophilous Graph Learning

2 citations · 3 across the 8 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG2026

Sparse-Aware Neural Networks for Nonlinear Functionals: Mitigating the Exponential Dependence on Dimension

Jianfei Li, Shuo Huang, Han Feng +2

Deep neural networks have emerged as powerful tools for learning operators defined over infinite-dimensional function spaces. However, existing theories frequently encounter diffic…

cs.LG2026

Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks

Luwei Sun, Dongrui Shen, Feng Chuanwen +3

Motivated by challenges in conditional generative modeling, where the target conditional density takes the form of a ratio f1 over f2, this paper develops a theoretical framework f…

cs.LG2024

Bridging Smoothness and Approximation: Theoretical Insights into Over-Smoothing in Graph Neural Networks

Guangrui Yang, Jianfei Li, Ming Li +2

In this paper, we explore the approximation theory of functions defined on graphs. Our study builds upon the approximation results derived from the -functional. We establish a t…

cs.LG2024

Convergence Analysis for Deep Sparse Coding via Convolutional Neural Networks

Jianfei Li, Han Feng, Ding-Xuan Zhou

In this work, we explore the intersection of sparse coding theory and deep learning to enhance our understanding of feature extraction capabilities in advanced neural network archi…

cs.LG2023★ 2 cited

Permutation Equivariant Graph Framelets for Heterophilous Graph Learning

Jianfei Li, Ruigang Zheng, Han Feng +2

The nature of heterophilous graphs is significantly different from that of homophilous graphs, which causes difficulties in early graph neural network models and suggests aggregati…

cs.LG2022★ 1 cited

SignReLU neural network and its approximation ability

Jianfei Li, Han Feng, Ding-Xuan Zhou

Deep neural networks (DNNs) have garnered significant attention in various fields of science and technology in recent years. Activation functions define how neurons in DNNs process…