Inicio  /  Applied Sciences  /  Vol: 12 Par: 20 (2022)  /  Artículo
ARTÍCULO
TITULO

Graph Convolutional Networks Guided by Explicitly Estimated Homophily and Heterophily Degree

Rui Zhang and Xin Li    

Resumen

Graph convolutional networks (GCNs) have been successfully applied to learning tasks on graph-structured data. However, most traditional GCNs based on graph convolutions assume homophily in graphs, which leads to a poor performance when dealing with heterophilic graphs. Although many novel methods have recently been proposed to deal with heterophily, the effect of homophily and heterophily on classifying node pairs is not clearly separated in existing approaches and inevitably influences each other. To deal with various types of graphs more accurately, in this work we propose a new GCN-based model that leverages the explicitly estimated homophily and heterophily degree between node pairs and adaptively guides the propagation and aggregation of signed messages. We also design a pre-training process to learn homophily and heterophily degree from both original node attributes that are graph-agnostic and the localized graph structure information by using Deepwalk that reflects graph topology. Extensive experiments on eight real-world benchmarks demonstrate that the new approach achieves state-of-the-art results on three homophilic graph datasets and outperforms baselines on five heterophilic graph datasets.

 Artículos similares

       
 
Meng Wu and Pudong Shi    
To address the problem of poor detection and under-utilization of the spatial relationship between nodes in human pose estimation, a method based on an improved spatial temporal graph convolutional network (ST-GCN) model is proposed. Firstly, upsampling ... ver más
Revista: Applied Sciences

 
Yifei Wang, Yongwei Wang, Hao Hu, Shengnan Zhou and Qinwu Wang    
In order to solve the current problems in domain long text classification tasks, namely, the long length of a document, which makes it difficult for the model to capture key information, and the lack of expert domain knowledge, which leads to insufficien... ver más
Revista: Applied Sciences

 
Zhihong Chang, Chunsheng Liu and Jianmin Jia    
As an important component of intelligent transportation-management systems, accurate traffic-parameter prediction can help traffic-management departments to conduct effective traffic management. Due to the nonlinearity, complexity, and dynamism of highwa... ver más
Revista: Applied Sciences

 
Enyu Yu, Yan Fu, Junlin Zhou, Hongliang Sun and Duanbing Chen    
Many real-world systems can be expressed in temporal networks with nodes playing different roles in structure and function, and edges representing the relationships between nodes. Identifying critical nodes can help us control the spread of public opinio... ver más
Revista: Applied Sciences

 
Chunwei Hu, Xianfeng Liu, Sheng Wu, Fei Yu, Yongkun Song and Jin Zhang    
Accurate crowd flow prediction is essential for traffic guidance and traffic control. However, the high nonlinearity, temporal complexity, and spatial complexity that crowd flow data have makes this problem challenging. This research proposes a dynamic g... ver más
Revista: Applied Sciences