Class ProgressiveInverseUserMetricReranker<U>
java.lang.Object
es.uam.eps.ir.ranksys.novdiv.reranking.PermutationReranker<U,I>
es.uam.eps.ir.ranksys.novdiv.reranking.GreedyReranker<U,I>
es.uam.eps.ir.relison.links.recommendation.reranking.local.LambdaReranker<U,U>
es.uam.eps.ir.relison.links.recommendation.reranking.local.user.UserMetricReranker<U>
es.uam.eps.ir.relison.links.recommendation.reranking.local.user.ProgressiveInverseUserMetricReranker<U>
- Type Parameters:
U
- type of the users.
- All Implemented Interfaces:
es.uam.eps.ir.ranksys.novdiv.reranking.Reranker<U,U>
public class ProgressiveInverseUserMetricReranker<U> extends UserMetricReranker<U>
Implementation of a reranking strategy for contact recommendation that demotes the
average value of some vertex metric in the resulting network.
Individually reranks each recommendation.
-
Nested Class Summary
Nested Classes Modifier and Type Class Description protected class
ProgressiveInverseUserMetricReranker.ProgressiveInverseUserMetricUserReranker
The class for generating the reranking.Nested classes/interfaces inherited from class es.uam.eps.ir.relison.links.recommendation.reranking.local.user.UserMetricReranker
UserMetricReranker.UserMetricUserReranker
Nested classes/interfaces inherited from class es.uam.eps.ir.relison.links.recommendation.reranking.local.LambdaReranker
LambdaReranker.LambdaUserReranker
-
Field Summary
Fields inherited from class es.uam.eps.ir.relison.links.recommendation.reranking.local.user.UserMetricReranker
graph, metric
Fields inherited from class es.uam.eps.ir.relison.links.recommendation.reranking.local.LambdaReranker
lambda
-
Constructor Summary
Constructors Constructor Description ProgressiveInverseUserMetricReranker(double lambda, int cutoff, java.util.function.Supplier<Normalizer<U>> norm, Graph<U> graph, VertexMetric<U> metric)
Constructor. -
Method Summary
Modifier and Type Method Description protected es.uam.eps.ir.ranksys.novdiv.reranking.GreedyReranker.GreedyUserReranker<U,U>
getUserReranker(es.uam.eps.ir.ranksys.core.Recommendation<U,U> recommendation, int maxLength)
Methods inherited from class es.uam.eps.ir.relison.links.recommendation.reranking.local.LambdaReranker
rerankPermutation
-
Constructor Details
-
ProgressiveInverseUserMetricReranker
public ProgressiveInverseUserMetricReranker(double lambda, int cutoff, java.util.function.Supplier<Normalizer<U>> norm, Graph<U> graph, VertexMetric<U> metric)Constructor.- Parameters:
lambda
- trade-off between the original recommendation score and the metric we want to promote.cutoff
- the size of the recommendation ranking.norm
- the normalization approach.graph
- the graph we want to use.metric
- the vertex metric to demote.
-
-
Method Details
-
getUserReranker
protected es.uam.eps.ir.ranksys.novdiv.reranking.GreedyReranker.GreedyUserReranker<U,U> getUserReranker(es.uam.eps.ir.ranksys.core.Recommendation<U,U> recommendation, int maxLength)- Specified by:
getUserReranker
in classLambdaReranker<U,U>
-