Module org.jgrapht.core
Package org.jgrapht.alg.linkprediction

Class HubDepressedIndexLinkPrediction<V,E>

java.lang.Object
org.jgrapht.alg.linkprediction.HubDepressedIndexLinkPrediction<V,E>
Type Parameters:
V - the graph vertex type
E - the graph edge type
All Implemented Interfaces:
LinkPredictionAlgorithm<V,E>
public class HubDepressedIndexLinkPrediction<V,E> extends Object implements LinkPredictionAlgorithm<V,E>
Predict links using the Hub Depressed Index.

This is a local method which computes $s_{xy} = \frac{2|\Gamma(u)\cap\Gamma(v))|}{max(k(u),k(v))}$ where for a node $v$, $\Gamma(v)$ denotes the set of neighbors of $v$ and $k(v) = |\Gamma(v)|$ denotes the degree of $v$.

See the following paper:
  • E. Ravasz, A.L. Somera, D.A. Mongru, Z.N. Oltvai, A.-L. Barabási, Science 297, 1553 (2002)
Author:
Dimitrios Michail

  • Constructor Details

    • HubDepressedIndexLinkPrediction

      public HubDepressedIndexLinkPrediction(Graph<V,E> graph)
      Create a new prediction
      Parameters:
      graph - the input graph

  • Method Details

    • predict

      public double predict(V u, V v)
      Description copied from interface: LinkPredictionAlgorithm
      Predict an edge between two vertices. The magnitude and the interpretation of the returned score depend solely on the algorithm.
      Specified by:
      predict in interface LinkPredictionAlgorithm<V,E>
      Parameters:
      u - first vertex
      v - second vertex
      Returns:
      a prediction score