3.8 Proceedings Paper

Graph Neural Network Sensitivity Under Probabilistic Error Model

出版社

IEEE

关键词

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

向作者/读者索取更多资源

This paper investigates the impact of a probabilistic graph error model on the performance of graph convolutional networks (GCNs). The paper proves the upper bound of the adjacency matrix under the error model and analytically specifies the upper bound of a normalized adjacency matrix with self-loop added. Experiments on a synthetic dataset are conducted to illustrate the error bounds and study the sensitivity of a simple GCN under this probabilistic error model on accuracy.
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.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

3.8
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据