Types of graph learning tasks
We have discussed graphs and the basic principles of GNNs but what type of tasks can be performed using GNNs on graph data? (By tasks, we are referring to the downstream tasks mentioned in the previous section.) Broadly, there are three different categories of graph learning tasks:
- Node-level tasks
- Edge-level tasks
- Graph-level tasks
Let us briefly discuss these.
Understanding node-level tasks
Node-level tasks are aimed at predicting the class of a given node within a graph. Our demonstrations in the previous sections (in Figure 6.3) are based on node-level tasks where the task was to predict the gender of each node – male, female, or other. For such tasks, the latent feature representations of each node (final output of the node’s computational graph) are used to train a downstream task.
This task can be:
- A classification task – involving discrete labels (gender, color, etc.) ...