ChebNet involves a formulation of CNNs in the context of spectral graph theory, which provides the necessary mathematical background and efficient numerical schemes to design fast localized convolutional filters on graphs.
Description from: Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
Source: Convolutional Neural Networks on Graphs with Fast Localized Spectral FilteringPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Node Classification | 3 | 33.33% |
GPR | 2 | 22.22% |
Graph Learning | 1 | 11.11% |
Graph Neural Network | 1 | 11.11% |
Node Classification on Non-Homophilic (Heterophilic) Graphs | 1 | 11.11% |
Skeleton Based Action Recognition | 1 | 11.11% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |