SSGCN: a sampling sequential guided graph convolutional network

doi:10.1007/s13042-023-02013-2

2023-11-14

PRE

DOI：10.1007/s13042-023-02013-2

原文链接

原文求助

摘要

En 中文

Graph convolutional networks(GCNs) have become one of the important technologies for solving graph structured data problems. GCNs utilize convolutional networks to learn node and spatial features in the graph, and fully fuse them for node classification tasks. Consequently, for most GCNs, graph convolution operation over the set of nodes is the key. Nevertheless, such an operation is frequently embedded into a fixed graph without considering the dynamic variation of the set of nodes. Immediately, the incremental learning mechanism can be considered. From this viewpoint, a Sampling Sequential Guided Graph Convolutional Network (SSGCN) is developed. Firstly, through random sampling over the set of nodes, multiple minibatch graphs can be obtained. Secondly, by the proposed sequential guidance, the weight matrices can be updated incrementally by using graph convolution over minibatch graphs one by one. That is, the trained weight matrix of the previous minibatch graph is saved, which in turn is used as an input for training the next minibatch graph. Finally, the prediction results from all minibatch graph learners are integrated. We conducted experiments based on the standard variance of different tau number of losses, and over three common citation network datasets (Cora, Citeseer and Pubmed) to evaluate the performance of SSGCN in node classification tasks. The experimental results show that, in comparison study and ablation study,in terms of both efficiency and effectiveness, the performance of SSGCN is superior to most state-of-the-art methods. In addition, SSGCN shows good convergence in visualization.

Keyword:

Graph convolutional networks

Incremental learning

Minibatch graph

Random sampling

Sequential guidance

期刊

International Journal of Machine Learning and Cybernetics

IF:

2.7

论文数:

3.2K

被引数:

5.6K

机构

jiangsu university of science & technology

学者数:

9.0K

论文数: 6.9K

被引数: 9

引用论文

An Electronic Infrastructure for Research and Treatment of the Thalassemias and Other Hemoglobinopathies: The Euro-Mediterranean Ithanet Project

Hemoglobin

IF0

2009-09-15

PREAI

Carsten W. Lederer; A. Nazli Basak; Yesim Aydinok; Soteroula Christou; Amal El-Beshlawy; Androulla Eleftheriou; Slaheddine Fattoum; Alex E. Felice; Eitan Fibach; Renzo Galanello; Roberto Gambari; Lucian Gavrila; Piero C. Giordano; Frank Grosveld; Helen Hassapopoulou; Eva Hladka; Emmanuel Kanavakis; Franco Locatelli; John Old; George P. Patrinos; Giovanni Romeo; Ali Taher; Joanne Traeger-Synodinos; Panayiotis Vassiliou; Ana Villegas; Ersi Voskaridou; Henri Wajcman; Anastasios Zafeiropoulos; Marina Kleanthous

Phase retrieval using unitary 2-designs

2017 International Conference on Sampling Theory and Applications (SampTA)

IF0

2017-07-01