stable graph filter

[[concept]]
Stable Graph Filter

Let S be a graph shift operator and S=fϵ(S) some perturbation for some ϵ>0. Let H be a graph filter. We say H is stable to the perturbation f if

||SS||p0 as ϵ0

Mentions

File
GNNs perform better than their constituent filters
Lipschitz filters are stable to additive perturbations
integral Lipschitz filters are stable to relative perturbations
integral lipschitz filters are stable to dilations
stability and size tradeoff for realistic sparsity pattern considerations setting
stability-discriminability tradeoff for Lipschitz filters
2025-03-05 graphs lecture 12
2025-03-10 graphs lecture 13
2025-03-24 graphs lecture 14
2025-04-09 lecture 19