5,337
edits
Graph neural network: Difference between revisions
no edit summary
No edit summary |
No edit summary |
||
| Line 1: | Line 1: | ||
If you can represent your data as a graph, you can use a graph neural network to perform inference on the | If you can represent your data as a graph, you can use a graph neural network to perform inference on it.<br> | ||
GNN operate on global graph embeddings or local embeddings in each node or edge in the graph.<br> | |||
Hence, a GNN allows you to output predictions on each node, each edge, or the entire graph. | |||
==Introduction== | ==Introduction== | ||
===Structure=== | ===Structure=== | ||
A graph neural network consists of layers which operate on graphs. | A graph neural network consists of layers which operate on graphs.<br> | ||
Typically, this means one or more GNN layers to get new embeddings along the graph.<br> | |||
Then a standard MLP can be used to parse each embedding into logits or values. | |||
At each layer, you get the following features during inference: | At each layer, you get the following features during inference: | ||