MHMan Hu

Man Hu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Man Hu has a total of 15 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Experimental analysis of position embedding in graph transformer networks

    by Man Hu, Dezhi Sun, Zhenyu Li

    The Transformer structures have achieved excellent performances in an increasing number of fields. In the field of natural language processing, the original Transformer structure was used to work on a full connectivity graph, which depicts all connections between words in a phrase. It has been subsequently applied in areas such as computer vision. Recently, many studies have attempted to apply Transformer structures to graph data and achieved good performance. However, it is still a challenge to embedding the structural information of the graph data. To understand the representation of graph data, we employed three distinct ways of embedding the positional and structural information of graph data based on the Transformer structure in this work. To learn the feature representation of the graph data, the encoded structural information and original feature information of the graph data were fed into the Transformer structure. For the learned feature representations, we used them for node classification and graph regression, and then compared and analyzed the three different encoding methods.

  • An evolutionary analysis approach based on core-edge structured communities for data mining

    by Zhenyu Li, Dezhi Sun, Man Hu

    With the rapid development of communication technology and social media, people are constantly interacting with each other, generating a large amount of behavioral data and forming a complex social network. With time, the interaction behaviors between people also change, which results in a constantly changing social network. Analysis of evolutionary social networks can effectively mining people's behavioral data, understanding people's behavior models in depth. Community detection is one of the important methods for social network analysis, and evolutionary analysis of dynamically changing communities, especially the core stable community structure in dynamic networks, can reveal the community structure at different periods and reveal the social network evolution patterns. In this paper, we define communities on real complex networks as core-edge structures with a tight core and sparse periphery, which can represent the importance of nodes within the community. And we propose a community detection algorithm based on the core-edge structure communities. Moreover, based on the characteristics of the core-edge community structure, we propose a community similarity calculation method based on the importance of members and an evolution analysis method based on the core-edge community structure.

  • Open Access

    Adaptive Aggregation-Transformation Decoupled Graph Convolutional Network for Semi-Supervised Learning

    by Dezhi Sun, Man Hu, Zhenyu Li

    Graph Convolutional Network (GCN) has achieved significant success in many graph representation learning tasks. GCN usually learns graph representations by performing Neighbor Aggregation (NA) and Feature Transformation (FT) operations. Deep Adaptive Graph Neural Network (DAGNN) improves NA operation in the aggregation-transformation decoupled GCN, which enables the model to obtain a large receiver field. However, the problem with GCN is that when the model is trained to a deeper level, the performance decreases. In particular, the influence of NA and FT on model degradation has not been fully considered. In this work, we propose a new decoupled GCN architecture to enhance the performance of deep GCN. First, we conduct an experimental analysis of the impact of NA and FT operations on the degradation of the deep GCN model. Subsequently, we propose an Adaptive Aggregation-Transform Decoupled Graph Convolutional Network (AATD-GCN) which divides the model into two depths $D_{NA}$ and $D_{FT}$ , and proposes improved approaches in NA and FT, respectively. The AATD-GCN reduces the influence of NA and FT operations on performance degradation of deep GCN, and obtains a large receiver field while extracting complex feature information. We investigate the requirements of model depth $D_{NA}$ and $D_{FT}$ for graphs of different structures and sizes. Finally, the effectiveness of the proposed architecture is verified through extensive experiments on real-world datasets, the experimental results show that AATD-GCN is superior in terms of accuracy and robustness.


  • AP-BERT: enhanced pre-trained model through average pooling

    by Shuai Zhao, Tianyu Zhang, Man Hu, Wen Chang, Fucheng You


  • Open Access

    Research on animal image classification based on transfer learning

    by Man Hu, Fucheng You

    Training a convolutional neural network requires a large number of sample data and a large amount of computing power. In some practical application scenarios, there may be difficulties in sample data collection and complex network model construction. To improve the classification accuracy and fitting speed of the convolutional neural network, a transfer learning classification method for an animal image is proposed. The fully connected layer of the pre-trained ResNet18 network is modified, and the eight animals in the animal-10 dataset on Kaggle are used to fine-tune the network model. The best classification accuracy of the obtained network model for a single animal is 97%, and the classification accuracy for all animals is 92%. Compared with the model that did not use transfer learning training, this kind of transfer learning network model has a great improvement in accuracy and fitting speed.


  • Open Access

    Research on Blended Learning Mode Based on the Course of Engine Principle

    by Fei Wu, Man Hu, Yunwu Li, Jie Ji

    This article deals with the problem of low participation of students as well as their poor understanding in the course of “Engine Principle”. In this paper, the current situation and characteristics of the curriculum are analyzed. With the advantages of MOOC, the authors tend to explore blended learning model, which is composed of online knowledge obtaining and offline flipped class. The design and practice of the model is implemented in three aspects: teaching contents, class organization and assessment. We recorded teaching videos and related course materials based on knowledge points and uploaded them to the Mooc platform. Tests run through the whole training process in each stage in order to evaluate the effect of blended learning mode. This blended learning model has balanced traditional teaching and modern teaching advantage. Furthermore, the ability of students to put what they have learned into practice and the ability to innovate has been promoted. With the blended learning mode based on MOOC, it is a better way to solve the problems of low participation and poor understanding and application ability of students in the current teaching.