Han Feng

Prof. Han Feng

orcid

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 March 2024 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
JLJianfei Li
Jianfei Li
RZRuigang Zheng
Ruigang Zheng
HFHan Feng
Han Feng
MLMing Li
Ming Li
Xiaosheng ZhuangXiaosheng Zhuang
Xiaosheng Zhuang
The nature of heterophilous graphs is significantly different from that of homophilous graphs, which causes difficulties in early graph neural network (GNN) models and suggests aggregations beyond the one-hop neighborhood. In this article, we develop a new way to implement multiscale extraction via constructing Haar-type graph framelets with desired properties of permutation equivariance, efficiency, and sparsity, for deep learning tasks on graphs. We further design a graph framelet neural network model permutation equivariant graph framelet augmented network (PEGFAN) based on our constructed graph framelets. The experiments are conducted on a synthetic dataset and nine benchmark datasets to compare the performance with other state-of-the-art models. The result shows that our model can achieve the best performance on certain datasets of heterophilous graphs (including the majority of heterophilous datasets with relatively larger sizes and denser connections) and competitive performance on the remaining.

1 November 2020 in Neural Networks
Verified
Journal Article
Closed access
ZFZhiying Fang
Zhiying Fang
HFHan Feng
Han Feng
SHShuo Huang
Shuo Huang
DZDing-Xuan Zhou
Ding-Xuan Zhou

6 October 2025 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
GYGuangrui Yang
Guangrui Yang
MLMing Li
Ming Li
HFHan Feng
Han Feng
Xiaosheng ZhuangXiaosheng Zhuang
Xiaosheng Zhuang
Graph convolutional networks (GCNs) have emerged as powerful models for graph learning tasks, exhibiting promising performance in various domains. While their empirical success is evident, there is a growing need to understand their essential ability from a theoretical perspective. Existing theoretical research has primarily focused on the analysis of single-layer GCNs, while a comprehensive theoretical exploration of the stability and generalization of deep GCNs remains limited. In this paper, we bridge this gap by delving into the stability and generalization properties of deep GCNs, aiming to provide valuable insights by characterizing rigorously the associated upper bounds. Our theoretical results reveal that the stability and generalization of deep GCNs are influenced by certain key factors, such as the maximum absolute eigenvalue of the graph filter operators and the depth of the network. Our theoretical studies contribute to a deeper understanding of the stability and generalization properties of deep GCNs, potentially paving the way for developing more reliable and well-performing models.

23 December 2021 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
HFHan Feng
Han Feng
SHShuo Huang
Shuo Huang
DZDing-Xuan Zhou
Ding-Xuan Zhou
Deep learning based on deep convolutional neural networks (CNNs) is extremely efficient in solving classification problems in speech recognition, computer vision, and many other fields. But there is no enough theoretical understanding about this topic, especially the generalization ability of the induced CNN algorithms. In this article, we develop some generalization analysis of a deep CNN algorithm for binary classification with data on spheres. An essential property of the classification problem is the lack of continuity or high smoothness of the target function associated with a convex loss function such as the hinge loss. This motivates us to consider the approximation of functions in the $L_p$ space with 1≤ p ≤ ∞. We provide rates of $L_p$ -approximation when the approximated function lies in a Sobolev space and then present generalization bounds and learning rates for the excess misclassification error of the deep CNN classification algorithm. Our novel analysis is based on efficient cubature formulae on spheres and other tools from spherical analysis and approximation theory.

20 January 2019 in International Journal of Food Properties
Verified
Journal Article
Open access
YJYi Jin
Yi Jin
Kok Wai WongKok Wai Wong
Kok Wai Wong
ZWZidan Wu
Zidan Wu
DQDebo Qi
Debo Qi
RWRui Wang
Rui Wang
WWWenfu Wu
Wenfu Wu
In this paper, a model for controlling paddy drying by incorporating accumulated temperature is introduced and defined. Drying experiments using freshly harvested paddy were conducted at different levels of drying air parameters including temperature (T = 27°C, 31°C, 35°C, 39°C, and 43°C), relative humidity (RH = 45%, 50%, 55%, 60%, and 65%), initial moisture content (M0 = 17%, 19%, 21%, 23%, and 25%) and airspeed (V = 0.4, 0.5, 0.6, 0.7, and 0.8 m s−1). When T = 31°C, RH = 60%, M0 = 19%, and V = 0.5 ms−1, the crack additional percentage reached a minimum value of 0.508%, with the average precipitation rate at 0.719%·h. Further, an accumulated temperature and quality chart was provided in this paper. The x-coordinate of this chart is temperature, and the initial moisture content represents the y-coordinate. It covers the drying conditions of the actual dryer well and has a wide range of applicability for real-world environment. The model developed in this study not only provides a scientific reference for precise drying and intelligent control of paddy but also guide the actual drying operation.

1 January 2022 in Mathematical Foundations of Computing
Verified
Journal Article
Closed access
PDF file
HFHan Feng
Han Feng
SHSizai Hou
Sizai Hou
LWLe-Yin Wei
Le-Yin Wei
DZDing-Xuan Zhou
Ding-Xuan Zhou
Readability of Chinese texts considered in this paper is a multi-class classification problem with \begin{document}$ 12 $\end{document} grade classes corresponding to \begin{document}$ 6 $\end{document} grades in primary schools, \begin{document}$ 3 $\end{document} grades in middle schools, and \begin{document}$ 3 $\end{document} grades in high schools. A special property of this problem is the strong ambiguity in determining the grades. To overcome the difficulty, a measurement of readability assessment methods used empirically in practice is adjacent accuracy in addition to exact accuracy. In this paper we give mathematical definitions of these concepts in a learning theory framework and compare these two quantities in terms of the ambiguity level of texts. A deep learning algorithm is proposed for readability of Chinese texts, based on convolutional neural networks and a pre-trained BERT model for vector representations of Chinese characters. The proposed CNN model can extract sentence and text features by convolutions of sentence representations with filters and is efficient for readability assessment, which is demonstrated with some numerical experiments.