# What are the meanings of Node Classification, Link Prediction, Graph Classification in Graph Neural Network?

I am currently studying Graph Neural Network but I have some difficulty in understanding what I can do after having studied Graph Neural Network. From having gained a bit of understand in Graph Neural Network, I can do Node Classification, Link Prediction, and Graph Classification but I don't really understand what those 3 terms mean.

It is like I can study and understand how node embedding works with math but don't really understand where to use it. While studying this topic, all the contents explains where I can use it but those explanations are not really clear to me.

Hope somebody gives me clears examples of the three terms in my question.

• Did you want definitions, or did you want examples? Aug 9, 2021 at 13:49
• Examples will do. Aug 10, 2021 at 12:39

Different problems that you can can tackle using a graph representation. A graph is defined as a set of <V,E> (nodes , links).

Think of 2 examples.

1. atoms and their bonds (making together a molecule). in this case V= atoms, E= chmical bonds, graph is molecule

2. users in social network being connected if they are friends (making together a social network. in this case V= users, E= chmical bonds, graph is molecule

For Node classification given many valid molecules (training data) and given a new incomplete data (molecule with unknown atoms comprising it ) ask the model to tell you with atom of the periodic table of chemical elements it is. This can be seen as a property of the node.

For link classification in the example 2 given example of users that are friends and not friends, ask the network if 2 users are friends or not.

For graph classification imagine now that you want to specify some molecules are safe to consume and not safe to consume by humans.