Semi supervised learning on graphs

I have the following semi-supervised problem:

I have a graph of persons and their relations. 
Some of those persons have a predefined risk classification. Classify the risk of the other nodes.

I know risk is kind of arbitrary that's why I'm open to any ideas.

An example is, suppose I have a person with classification critical (10) and I wanted to find the risk classification of their neighborhood. I thought on doing something like for every node, for every fixed risk node, subtract the risk of this node by the distance of the fixed node to the node we are analyzing and then getting the maximum of it. But this doesn't account for the fact that a node may have several critical nodes that are in his neighborhood and this should increase his risk.

Those anyone know any algorithm that may help me?