Graph neural network: Difference between revisions

(One intermediate revision by the same user not shown)

Line 1:

If you can represent your data as a graph, you can use a graph neural network to perform inference on the ~~data and~~ output ~~a new graph or~~ predictions on the graph.

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==

===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:

Line 26:

Line 29:

* [https://distill.pub/2021/gnn-intro/ A Gentle Introduction to Graph Neural Networks (2021) by Google Research]

* [https://distill.pub/2021/understanding-gnns/ Understanding Convolutions on Graphs (2021) by Google Research]

* [https://arxiv.org/abs/1812.08434 Graph Neural Networks: A Review of Methods and Applications (2018)]

@@ 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 data and output a new graph or predictions on the graph.
+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==
 ===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:
@@ Line 26: / Line 29: @@
 * [https://distill.pub/2021/gnn-intro/ A Gentle Introduction to Graph Neural Networks (2021) by Google Research]
 * [https://distill.pub/2021/understanding-gnns/ Understanding Convolutions on Graphs (2021) by Google Research]
+* [https://arxiv.org/abs/1812.08434 Graph Neural Networks: A Review of Methods and Applications (2018)]