Community Detection Algorithm.
The Vertex values of the input Graph provide the initial label assignments.
Initially, each vertex is assigned a tuple formed of its own initial value along with a score equal to 1.0.
The vertices propagate their labels and max scores in iterations, each time adopting the label with the
highest score from the list of received messages. The chosen label is afterwards re-scored using the fraction
delta/the superstep number. Delta is passed as a parameter and has 0.5 as a default value.