Class InterCommunityEdgeGiniComplement<U>
java.lang.Object
es.uam.eps.ir.relison.links.recommendation.reranking.global.local.LocalReranker<U,I>
es.uam.eps.ir.relison.links.recommendation.reranking.global.local.LocalGreedyReranker<U,I>
es.uam.eps.ir.relison.links.recommendation.reranking.global.local.LocalLambdaReranker<U,U>
es.uam.eps.ir.relison.links.recommendation.reranking.global.local.GraphLocalReranker<U>
es.uam.eps.ir.relison.links.recommendation.reranking.global.local.communities.InterCommunityReranker<U>
es.uam.eps.ir.relison.links.recommendation.reranking.global.local.communities.InterCommunityEdgeGiniComplement<U>
- Type Parameters:
U- type of the users
- All Implemented Interfaces:
GlobalReranker<U,U>
public class InterCommunityEdgeGiniComplement<U> extends InterCommunityReranker<U>
Implementation of a reranking strategy for balancing the distribution of edges between pairs
of communities. It only considers links between communities.
-
Field Summary
Fields Modifier and Type Field Description private java.util.List<java.lang.Double>matrixNumber of edges between communitiesprivate doublesumTotal number of edges between communities.Fields inherited from class es.uam.eps.ir.relison.links.recommendation.reranking.global.local.communities.InterCommunityReranker
communities, communityGraphFields inherited from class es.uam.eps.ir.relison.links.recommendation.reranking.global.local.GraphLocalReranker
graphFields inherited from class es.uam.eps.ir.relison.links.recommendation.reranking.global.local.LocalLambdaReranker
novMap, novStats, relStatsFields inherited from class es.uam.eps.ir.relison.links.recommendation.reranking.global.local.LocalGreedyReranker
cutOff -
Constructor Summary
Constructors Constructor Description InterCommunityEdgeGiniComplement(double lambda, int cutoff, java.util.function.Supplier<Normalizer<U>> norm, Graph<U> graph, Communities<U> communities)Constructor. -
Method Summary
Modifier and Type Method Description protected voidinnerUpdate(U user, org.ranksys.core.util.tuples.Tuple2od<U> tpld)Updates the different parameters of the reranker, further than changing the edges in the graph.protected doublenov(U u, org.ranksys.core.util.tuples.Tuple2od<U> tpld)Novelty score.protected voidupdate(es.uam.eps.ir.ranksys.core.Recommendation<U,U> reranked)Updates the values, given a new recommendation.Methods inherited from class es.uam.eps.ir.relison.links.recommendation.reranking.global.local.GraphLocalReranker
updateMethods inherited from class es.uam.eps.ir.relison.links.recommendation.reranking.global.local.LocalLambdaReranker
rerankPermutation, selectItem, valueMethods inherited from class es.uam.eps.ir.relison.links.recommendation.reranking.global.local.LocalGreedyReranker
getBasePerm, rerankRecommendationMethods inherited from class es.uam.eps.ir.relison.links.recommendation.reranking.global.local.LocalReranker
rerankRecommendations
-
Field Details
-
Constructor Details
-
InterCommunityEdgeGiniComplement
public InterCommunityEdgeGiniComplement(double lambda, int cutoff, java.util.function.Supplier<Normalizer<U>> norm, Graph<U> graph, Communities<U> communities)Constructor.- Parameters:
lambda- trade-off between the recommendation score and the novelty/diversity value.cutoff- number of elements to take.norm- the normalization strategy.graph- the original graph.communities- the relation between users and communities.
-
-
Method Details
-
nov
Description copied from class:LocalLambdaRerankerNovelty score.- Specified by:
novin classLocalLambdaReranker<U,U>- Parameters:
u- the target user.tpld- the recommended item and its recommendation score.- Returns:
- the novelty for this pair user-item.
-
innerUpdate
Description copied from class:GraphLocalRerankerUpdates the different parameters of the reranker, further than changing the edges in the graph.- Specified by:
innerUpdatein classGraphLocalReranker<U>- Parameters:
user- the target user.tpld- the new candidate user.
-
update
Description copied from class:LocalRerankerUpdates the values, given a new recommendation.- Specified by:
updatein classLocalReranker<U,U>- Parameters:
reranked- the reranked recommendation.
-