On the stability of polynomial spectral graph filters
Spectral graph filters are a key component in state-of-the-art machine learning models used for graph-based learning, such as graph neural networks. For certain tasks stability of the spectral graph filters is important for learning suitable representations. Understanding the type of structural pert...
Main Authors: | Kenlay, H, Thanou, D, Dong, X |
---|---|
Formato: | Conference item |
Idioma: | English |
Publicado em: |
IEEE
2020
|
Registos relacionados
Gaussian processes on graphs via spectral kernel learning
Por: Zhi, Y-C, et al.
Publicado em: (2023)
Por: Zhi, Y-C, et al.
Publicado em: (2023)
Registos relacionados
-
Interpretable stability bounds for spectral graph filters
Por: Kenlay, H, et al.
Publicado em: (2021) -
On the stability of graph convolutional neural networks under edge rewiring
Por: Kenlay, H, et al.
Publicado em: (2021) -
Structure-aware robustness certificates for graph classification
Por: Osselin, P, et al.
Publicado em: (2023) -
Robustness analysis of graph-based machine learning
Por: Kenlay, H
Publicado em: (2022) -
Graph similarity learning for change-point detection in dynamic networks
Por: Sulem, D, et al.
Publicado em: (2023)