Stability of Graph Convolutional Neural Networks through the lens of small perturbation analysis
CoRR(2023)
摘要
In this work, we study the problem of stability of Graph Convolutional Neural
Networks (GCNs) under random small perturbations in the underlying graph
topology, i.e. under a limited number of insertions or deletions of edges. We
derive a novel bound on the expected difference between the outputs of
unperturbed and perturbed GCNs. The proposed bound explicitly depends on the
magnitude of the perturbation of the eigenpairs of the Laplacian matrix, and
the perturbation explicitly depends on which edges are inserted or deleted.
Then, we provide a quantitative characterization of the effect of perturbing
specific edges on the stability of the network. We leverage tools from small
perturbation analysis to express the bounds in closed, albeit approximate,
form, in order to enhance interpretability of the results, without the need to
compute any perturbed shift operator. Finally, we numerically evaluate the
effectiveness of the proposed bound.
更多查看译文
关键词
Graph neural networks,graph signal processing,small perturbations analysis,stability,statistical bound
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要