Graph Models
FastGCN
Introduced by Chen et al. in FastGCN: Fast Learning with Graph Convolutional Networks via Importance SamplingFastGCN is a fast improvement of the GCN model recently proposed by Kipf & Welling (2016a) for learning graph embeddings. It generalizes transductive training to an inductive manner and also addresses the memory bottleneck issue of GCN caused by recursive expansion of neighborhoods. The crucial ingredient is a sampling scheme in the reformulation of the loss and the gradient, well justified through an alternative view of graph convoluntions in the form of integral transforms of embedding functions.
Description and image from: FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
Source: FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Node Classification | 3 | 30.00% |
| Graph Regression | 1 | 10.00% |
| Image Classification | 1 | 10.00% |
| Node Classification on Non-Homophilic (Heterophilic) Graphs | 1 | 10.00% |
| Relation Extraction | 1 | 10.00% |
| Sentiment Analysis | 1 | 10.00% |
| Skeleton Based Action Recognition | 1 | 10.00% |
| Text Classification | 1 | 10.00% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
