DGCNN 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 ClassificationPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Point Cloud Classification | 6 | 9.23% |
Adversarial Attack | 4 | 6.15% |
3D Point Cloud Classification | 4 | 6.15% |
Autonomous Driving | 4 | 6.15% |
Graph Neural Network | 3 | 4.62% |
Semantic Segmentation | 2 | 3.08% |
Classification | 2 | 3.08% |
Edge-computing | 2 | 3.08% |
Self-Supervised Learning | 2 | 3.08% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |