Graph Models
Deep Graph Convolutional Neural Network
Introduced by Zhang et al. in An End-to-End Deep Learning Architecture for Graph ClassificationDGCNN involves neural networks that read the graphs directly and learn a classification function. There are two main challenges: 1) how to extract useful features characterizing the rich information encoded in a graph for classification purpose, and 2) how to sequentially read a graph in a meaningful and consistent order. To address the first challenge, we design a localized graph convolution model and show its connection with two graph kernels. To address the second challenge, we design a novel SortPooling layer which sorts graph vertices in a consistent order so that traditional neural networks can be trained on the graphs.
Description and image from: An End-to-End Deep Learning Architecture for Graph Classification
Source: An End-to-End Deep Learning Architecture for Graph Classification
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Point Cloud Classification | 6 | 9.84% |
| Adversarial Attack | 4 | 6.56% |
| 3D Point Cloud Classification | 4 | 6.56% |
| Autonomous Driving | 4 | 6.56% |
| Semantic Segmentation | 2 | 3.28% |
| Classification | 2 | 3.28% |
| Edge-computing | 2 | 3.28% |
| Self-Supervised Learning | 2 | 3.28% |
| Decision Making | 2 | 3.28% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
