edu.cmu.minorthird.classify.ranking
Class ListNet

java.lang.Object
  edu.cmu.minorthird.classify.BatchClassifierLearner
      edu.cmu.minorthird.classify.BatchBinaryClassifierLearner
          edu.cmu.minorthird.classify.ranking.BatchRankingLearner
              edu.cmu.minorthird.classify.ranking.ListNet

All Implemented Interfaces:

BinaryClassifierLearner, ClassifierLearner, java.lang.Cloneable

public class ListNet
extends BatchRankingLearner

Implements the Listwise Ranking algorithm proposed at: Learning to Rank: From Pairwise Approach to Listwise Approach, ICML 2007. Zhe Cao, Tao Qin, Tie-Yan Liu, Ming-Feng Tsai, Hang Li. Only works for binary relevance levels (i.e., revelant vs non-revevant)

Author:

Vitor R. Carvalho

Field Summary

Fields inherited from class edu.cmu.minorthird.classify.BatchClassifierLearner

classifier, dataset

Constructor Summary

ListNet()

ListNet(int numEpochs)

ListNet(int epochs, double rate)

Method Summary

Classifier	batchTrain(Dataset data) subclasses should use this method to implement a batch supervised learning algorithm.
double	crossEntropy(double[] base, double[] b) Calculates Equation (3): cross entropy between a "base" distribution and another one.
void	setDevData(Dataset data)
void	setLearnRate()

Methods inherited from class edu.cmu.minorthird.classify.ranking.BatchRankingLearner

listsWithOneExampleEach, sortByScore, splitIntoRankings

Methods inherited from class edu.cmu.minorthird.classify.BatchBinaryClassifierLearner

batchTrainBinary, getBinaryClassifier, getSchema, setSchema

Methods inherited from class edu.cmu.minorthird.classify.BatchClassifierLearner

addExample, completeTraining, copy, getClassifier, hasNextQuery, nextQuery, reset, setInstancePool

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface edu.cmu.minorthird.classify.ClassifierLearner

addExample, completeTraining, copy, getClassifier, hasNextQuery, nextQuery, reset, setInstancePool

Constructor Detail

ListNet

public ListNet()

ListNet

public ListNet(int numEpochs)

ListNet

public ListNet(int epochs,
               double rate)

Method Detail

setDevData

public void setDevData(Dataset data)

batchTrain

public Classifier batchTrain(Dataset data)

Description copied from class: BatchClassifierLearner

subclasses should use this method to implement a batch supervised learning algorithm.

Specified by:

batchTrain in class BatchClassifierLearner

crossEntropy

public double crossEntropy(double[] base,
                           double[] b)

Calculates Equation (3): cross entropy between a "base" distribution and another one.

setLearnRate

public void setLearnRate()