Effects of Random Errors on Graph Convolutional Networks

Date
2022-01-04
Authors
Ando, Shinnosuke
Tsugawa, Sho
Contributor
Advisor
Department
Instructor
Depositor
Speaker
Researcher
Consultant
Interviewer
Journal Title
Journal ISSN
Volume Title
Publisher
Volume
Number/Issue
Starting Page
Ending Page
Alternative Title
Abstract
The use of Graph Convolutional Networks (GCN) has been an emerging trend in the network science research community. While GCN achieves excellent performance in several tasks, there exists an open issue in applying GCN to real-world applications. The issue is the effects of network errors on GCN. Since real-world network data contain several types of noises and errors, GCN is desirable to be less affected by such errors. However, the effects have not been sufficiently evaluated before. In this paper, we analyze the effects of random errors on GCN through extensive experiments. The results show that the node classification accuracy of GCN is decreased only 5% even when 50% of the edges are randomly increased or decreased. Moreover, in terms of false labels, the accuracy of node classification is decreased only 10% even when 20% of the labels are changed.
Description
Keywords
Network Analysis of Digital and Social Media, graph convolutional networks, network analysis, robustness
Citation
Extent
10 pages
Format
Geographic Location
Time Period
Related To
Proceedings of the 55th Hawaii International Conference on System Sciences
Rights
Attribution-NonCommercial-NoDerivatives 4.0 International
Rights Holder
Email libraryada-l@lists.hawaii.edu if you need this content in ADA-compliant format.