Graph Neural Network Sensitivity Under Probabilistic Error Model

Loading...
Thumbnail Image

Access rights

openAccess
publishedVersion

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Date

2022

Major/Subject

Mcode

Degree programme

Language

en

Pages

5

Series

2022 30th European Signal Processing Conference (EUSIPCO), pp. 2146-2150, European Signal Processing Conference

Abstract

Graph convolutional networks (GCNs) can successfully learn the graph signal representation by graph convolution. The graph convolution depends on the graph filter, which contains the topological dependency of data and propagates data features. However, the estimation errors in the propagation matrix (e.g., the adjacency matrix) can have a significant impact on graph filters and GCNs. In this paper, we study the effect of a probabilistic graph error model on the performance of the GCNs. We prove that the adjacency matrix under the error model is bounded by a function of graph size and error probability. We further analytically specify the upper bound of a normalized adjacency matrix with self-loop added. Finally, we illustrate the error bounds by running experiments on a synthetic dataset and study the sensitivity of a simple GCN under this probabilistic error model on accuracy.

Description

Publisher Copyright: © 2022 European Signal Processing Conference, EUSIPCO. All rights reserved.

Keywords

graph neural network, Graph signal processing, probabilistic error model, stability

Other note

Citation

Wang, X, Ollila, E & Vorobyov, S A 2022, Graph Neural Network Sensitivity Under Probabilistic Error Model . in 2022 30th European Signal Processing Conference (EUSIPCO) . European Signal Processing Conference, IEEE, pp. 2146-2150, European Signal Processing Conference, Belgrade, Serbia, 29/08/2022 . < https://eurasip.org/Proceedings/Eusipco/Eusipco2022/pdfs/0002146.pdf >