A Graph Convolutional Network, or GCN, is an approach for semi-supervised learning on graph-structured data. It is based on an efficient variant of convolutional neural networks which operate directly on graphs. The choice of convolutional architecture is motivated via a localized first-order approximation of spectral graph convolutions. The model scales linearly in the number of graph edges and learns hidden layer representations that encode both local graph structure and features of nodes.
Source: Semi-Supervised Classification with Graph Convolutional NetworksPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Node Classification | 80 | 10.93% |
General Classification | 40 | 5.46% |
Graph Learning | 34 | 4.64% |
Graph Classification | 26 | 3.55% |
Action Recognition | 25 | 3.42% |
Link Prediction | 24 | 3.28% |
Skeleton Based Action Recognition | 22 | 3.01% |
Recommendation Systems | 20 | 2.73% |
Graph Embedding | 19 | 2.60% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |