Graph Models
CayleyNet
Introduced by Levie et al. in CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral FiltersThe core ingredient of CayleyNet is a new class of parametric rational complex functions (Cayley polynomials) allowing to efficiently compute spectral filters on graphs that specialize on frequency bands of interest. The model generates rich spectral filters that are localized in space, scales linearly with the size of the input data for sparsely-connected graphs, and can handle different constructions of Laplacian operators.
Description adapted from: CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filters
Source: CayleyNets: Graph Convolutional Neural Networks with Complex Rational Spectral Filters
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Community Detection | 1 | 20.00% |
| General Classification | 1 | 20.00% |
| Image Classification | 1 | 20.00% |
| Matrix Completion | 1 | 20.00% |
| Node Classification | 1 | 20.00% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
