19 March 2022 in Applied Intelligence
12 June 2025 in Information Fusion
12 April 2022 in IEEE Access
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.
1 January 2020 in Science Journal of Education
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.