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...
Những tác giả chính: | Kenlay, H, Thanou, D, Dong, X |
---|---|
Định dạng: | Conference item |
Ngôn ngữ: | English |
Được phát hành: |
IEEE
2020
|
Những quyển sách tương tự
-
Interpretable stability bounds for spectral graph filters
Bằng: Kenlay, H, et al.
Được phát hành: (2021) -
On the stability of graph convolutional neural networks under edge rewiring
Bằng: Kenlay, H, et al.
Được phát hành: (2021) -
Structure-aware robustness certificates for graph classification
Bằng: Osselin, P, et al.
Được phát hành: (2023) -
Robustness analysis of graph-based machine learning
Bằng: Kenlay, H
Được phát hành: (2022) -
Graph similarity learning for change-point detection in dynamic networks
Bằng: Sulem, D, et al.
Được phát hành: (2023)