Graph Models
Diffusion-Convolutional Neural Networks
Introduced by Atwood et al. in Diffusion-Convolutional Neural NetworksDiffusion-convolutional neural networks (DCNN) is a model for graph-structured data. Through the introduction of a diffusion-convolution operation, diffusion-based representations can be learned from graph structured data and used as an effective basis for node classification.
Description and image from: Diffusion-Convolutional Neural Networks
Source: Diffusion-Convolutional Neural Networks
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| General Classification | 42 | 8.43% |
| Semantic Segmentation | 35 | 7.03% |
| Image Classification | 31 | 6.22% |
| Classification | 29 | 5.82% |
| Object Recognition | 18 | 3.61% |
| Image Segmentation | 15 | 3.01% |
| Object Detection | 12 | 2.41% |
| Object | 11 | 2.21% |
| Deep Learning | 10 | 2.01% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
