本文介绍了Alec主动学习方法，通过Density Peaks聚类策略选择有代表性的样本请求人工标签，用于监督学习模型的构建。Alec在处理小规模、高成本标签获取场景中展现出高效性，通过实例演示了从arff数据集中进行分类的过程和结果评估。
监督学习：指在有标签的训练集上进行训练，学习这些标签与数据之间的联系。
无监督学习：指对训练集上的数据进行分类。与监督学习不同，这些数据没有标签。
主动学习:某些情况下，数据集中有标签的数据非常少或是数据没有标签。对数据进行人工标注标签成本又非常昂贵，此时可以选择一些数据，提出标注标签的请求，将这些数据提交给专家标注标签。
比如说：假设有M个没有标签的数据，可以选择其中N个数据交给专家进行标注标签。但是在其中选择数据的过程并不是随意的。可以通过对M个数据进行筛选，选出有代表性的数据进行询问。最后机器可以根据这N个标签建立模型。
ALEC主动学习
ALEC 主动学习是属于三支主动学习的一种。三支主动学习是基于聚类的主动学习，它的样本处于三种状态: 被查询、被分类、延迟处理。
如何选择具有代表性的数据：
ALEC采用的策略是基于Density Peak的聚类选取方案。
步骤如下：
- 以样本x为中心，r为半径的圆内的样本都纳入样本x的统计中，得出落入圆内的点的密度。
- 所有点都以r为大小确定自己的圆，并且统计各自的密度。
- 若有一个样本y的密度值要高于x，同时距离x最近，则取这个距离为l。
样本x的密度代表了这个点的重要性，距离l代表了样本x的独立性。重要性与独立性的乘积为样本x的代表性。
ALEC 主动学习的步骤如下：
- 根据 Density peaks 将数据组织成一棵树, 同时计算每个对象的代表性;
- 查询当前块里代表性最高的若干样本的标签;
- 如果被查询样本具有同样的标签, 则认为当前块为纯, 将其余样本全部打上同样标签;
- 否则将当前块分裂为两块, 递归到下一级的第 2步;
输入：arff数据集。
输出：分类正确个数以及准确率。
优化目标：可能没有优化目标。
package knn5;
import java.io.FileReader;
import java.util.*;
import weka.core.Instances;
public class Alec {
Instances dataset;
int maxNumQuery;
int numQuery;
double radius;
double[] densities;
double[] distanceToMaster;
int[] descendantDensities;
double[] priority;
double maximalDistance;
int[] masters;
int[] predictedLabels;
int[] instanceStatusArray;
int[] descendantRepresentatives;
int[] clusterIndices;
int smallBlockThreshold = 3;
public Alec(String paraFilename) {
try {
FileReader tempReader = new FileReader(paraFilename);
dataset = new Instances(tempReader);
dataset.setClassIndex(dataset.numAttributes() - 1);
tempReader.close();
} catch (Exception ee) {
System.out.println(ee);
System.exit(0);
} // Of fry
computeMaximalDistance();
clusterIndices = new int[dataset.numInstances()];
}// Of the constructor
public static int[] mergeSortToIndices(double[] paraArray) {
int tempLength = paraArray.length;
int[][] resultMatrix = new int[2][tempLength];// For merge sort.
int tempIndex = 0;
for (int i = 0; i < tempLength; i++) {
resultMatrix[tempIndex][i] = i;
} // Of for i
int tempCurrentLength = 1;
int tempFirstStart, tempSecondStart, tempSecondEnd;
while (tempCurrentLength < tempLength) {
for (int i = 0; i < Math.ceil((tempLength + 0.0) / tempCurrentLength / 2); i++) {
tempFirstStart = i * tempCurrentLength * 2;
tempSecondStart = tempFirstStart + tempCurrentLength;
tempSecondEnd = tempSecondStart + tempCurrentLength - 1;
if (tempSecondEnd >= tempLength) {
tempSecondEnd = tempLength - 1;
} // Of if
int tempFirstIndex = tempFirstStart;
int tempSecondIndex = tempSecondStart;
int tempCurrentIndex = tempFirstStart;
if (tempSecondStart >= tempLength) {
for (int j = tempFirstIndex; j < tempLength; j++) {
resultMatrix[(tempIndex + 1) % 2][tempCurrentIndex] = resultMatrix[tempIndex
% 2][j];
tempFirstIndex++;
tempCurrentIndex++;
} // Of for j
break;
} // Of if
while ((tempFirstIndex <= tempSecondStart - 1)
&& (tempSecondIndex <= tempSecondEnd)) {
if (paraArray[resultMatrix[tempIndex
% 2][tempFirstIndex]] >= paraArray[resultMatrix[tempIndex
% 2][tempSecondIndex]]) {
resultMatrix[(tempIndex + 1) % 2][tempCurrentIndex] = resultMatrix[tempIndex
% 2][tempFirstIndex];
tempFirstIndex++;
} else {
resultMatrix[(tempIndex + 1) % 2][tempCurrentIndex] = resultMatrix[tempIndex
% 2][tempSecondIndex];
tempSecondIndex++;
} // Of if
tempCurrentIndex++;
} // Of while
// Remaining part
for (int j = tempFirstIndex; j < tempSecondStart; j++) {
resultMatrix[(tempIndex + 1) % 2][tempCurrentIndex] = resultMatrix[tempIndex
% 2][j];
tempCurrentIndex++;
} // Of for j
for (int j = tempSecondIndex; j <= tempSecondEnd; j++) {
resultMatrix[(tempIndex + 1) % 2][tempCurrentIndex] = resultMatrix[tempIndex
% 2][j];
tempCurrentIndex++;
} // Of for j
} // Of for i
tempCurrentLength *= 2;
tempIndex++;
} // Of while
return resultMatrix[tempIndex % 2];
}// Of mergeSortToIndices
public double distance(int paraI, int paraJ) {
double resultDistance = 0;
double tempDifference;
for (int i = 0; i < dataset.numAttributes() - 1; i++) {
tempDifference = dataset.instance(paraI).value(i) - dataset.instance(paraJ).value(i);
resultDistance += tempDifference * tempDifference;
} // Of for i
resultDistance = Math.sqrt(resultDistance);
return resultDistance;
}// Of distance
public void computeMaximalDistance() {
maximalDistance = 0;
double tempDistance;
for (int i = 0; i < dataset.numInstances(); i++) {
for (int j = 0; j < dataset.numInstances(); j++) {
tempDistance = distance(i, j);
if (maximalDistance < tempDistance) {
maximalDistance = tempDistance;
} // Of if
} // Of for j
} // Of for i
System.out.println("maximalDistance = " + maximalDistance);
}// Of computeMaximalDistance
public void computeDensitiesGaussian() {
System.out.println("radius = " + radius);
densities = new double[dataset.numInstances()];
double tempDistance;
for (int i = 0; i < dataset.numInstances(); i++) {
for (int j = 0; j < dataset.numInstances(); j++) {
tempDistance = distance(i, j);
densities[i] += Math.exp(-tempDistance * tempDistance / radius / radius);
} // Of for j
} // Of for i
System.out.println("The densities are " + Arrays.toString(densities) + "\r\n");
}// Of computeDensitiesGaussian
public void computeDistanceToMaster() {
distanceToMaster = new double[dataset.numInstances()];
masters = new int[dataset.numInstances()];
descendantDensities = new int[dataset.numInstances()];
instanceStatusArray = new int[dataset.numInstances()];
descendantDensities = mergeSortToIndices(densities);
distanceToMaster[descendantDensities[0]] = maximalDistance;
double tempDistance;
for (int i = 1; i < dataset.numInstances(); i++) {
// Initialize.
distanceToMaster[descendantDensities[i]] = maximalDistance;
for (int j = 0; j <= i - 1; j++) {
tempDistance = distance(descendantDensities[i], descendantDensities[j]);
if (distanceToMaster[descendantDensities[i]] > tempDistance) {
distanceToMaster[descendantDensities[i]] = tempDistance;
masters[descendantDensities[i]] = descendantDensities[j];
} // Of if
} // Of for j
} // Of for i
System.out.println("First compute, masters = " + Arrays.toString(masters));
System.out.println("descendantDensities = " + Arrays.toString(descendantDensities));
}// Of computeDistanceToMaster
public void computePriority() {
priority = new double[dataset.numInstances()];
for (int i = 0; i < dataset.numInstances(); i++) {
priority[i] = densities[i] * distanceToMaster[i];
} // Of for i
}// Of computePriority
public int coincideWithMaster(int paraIndex) {
if (clusterIndices[paraIndex] == -1) {
int tempMaster = masters[paraIndex];
clusterIndices[paraIndex] = coincideWithMaster(tempMaster);
} // Of if
return clusterIndices[paraIndex];
}// Of coincideWithMaster
public int[][] clusterInTwo(int[] paraBlock) {
Arrays.fill(clusterIndices, -1);
// Initialize the cluster number of the two roots.
for (int i = 0; i < 2; i++) {
clusterIndices[paraBlock[i]] = i;
} // Of for i
for (int i = 0; i < paraBlock.length; i++) {
if (clusterIndices[paraBlock[i]] != -1) {
// Already have a cluster number.
continue;
} // Of if
clusterIndices[paraBlock[i]] = coincideWithMaster(masters[paraBlock[i]]);
} // Of for i
// The sub blocks.
int[][] resultBlocks = new int[2][];
int tempFistBlockCount = 0;
for (int i = 0; i < clusterIndices.length; i++) {
if (clusterIndices[i] == 0) {
tempFistBlockCount++;
} // Of if
} // Of for i
resultBlocks[0] = new int[tempFistBlockCount];
resultBlocks[1] = new int[paraBlock.length - tempFistBlockCount];
int tempFirstIndex = 0;
int tempSecondIndex = 0;
for (int i = 0; i < paraBlock.length; i++) {
if (clusterIndices[paraBlock[i]] == 0) {
resultBlocks[0][tempFirstIndex] = paraBlock[i];
tempFirstIndex++;
} else {
resultBlocks[1][tempSecondIndex] = paraBlock[i];
tempSecondIndex++;
} // Of if
} // Of for i
System.out.println("Split (" + paraBlock.length + ") instances "
+ Arrays.toString(paraBlock) + "\r\nto (" + resultBlocks[0].length + ") instances "
+ Arrays.toString(resultBlocks[0]) + "\r\nand (" + resultBlocks[1].length
+ ") instances " + Arrays.toString(resultBlocks[1]));
return resultBlocks;
}// Of clusterInTwo
public void vote(int[] paraBlock) {
int[] tempClassCounts = new int[dataset.numClasses()];
for (int i = 0; i < paraBlock.length; i++) {
if (instanceStatusArray[paraBlock[i]] == 1) {
tempClassCounts[(int) dataset.instance(paraBlock[i]).classValue()]++;
} // Of if
} // Of for i
int tempMaxClass = -1;
int tempMaxCount = -1;
for (int i = 0; i < tempClassCounts.length; i++) {
if (tempMaxCount < tempClassCounts[i]) {
tempMaxClass = i;
tempMaxCount = tempClassCounts[i];
} // Of if
} // Of for i
// Classify unprocessed instances.
for (int i = 0; i < paraBlock.length; i++) {
if (instanceStatusArray[paraBlock[i]] == 0) {
predictedLabels[paraBlock[i]] = tempMaxClass;
instanceStatusArray[paraBlock[i]] = 2;
} // Of if
} // Of for i
}// Of vote
public void clusterBasedActiveLearning(double paraRatio, int paraMaxNumQuery,
int paraSmallBlockThreshold) {
radius = maximalDistance * paraRatio;
smallBlockThreshold = paraSmallBlockThreshold;
maxNumQuery = paraMaxNumQuery;
predictedLabels = new int[dataset.numInstances()];
for (int i = 0; i < dataset.numInstances(); i++) {
predictedLabels[i] = -1;
} // Of for i
computeDensitiesGaussian();
computeDistanceToMaster();
computePriority();
descendantRepresentatives = mergeSortToIndices(priority);
System.out.println(
"descendantRepresentatives = " + Arrays.toString(descendantRepresentatives));
numQuery = 0;
clusterBasedActiveLearning(descendantRepresentatives);
}// Of clusterBasedActiveLearning
public void clusterBasedActiveLearning(int[] paraBlock) {
System.out.println("clusterBasedActiveLearning for block " + Arrays.toString(paraBlock));
int tempExpectedQueries = (int) Math.sqrt(paraBlock.length);
int tempNumQuery = 0;
for (int i = 0; i < paraBlock.length; i++) {
if (instanceStatusArray[paraBlock[i]] == 1) {
tempNumQuery++;
} // Of if
} // Of for i
if ((tempNumQuery >= tempExpectedQueries) && (paraBlock.length <= smallBlockThreshold)) {
System.out.println("" + tempNumQuery + " instances are queried, vote for block: \r\n"
+ Arrays.toString(paraBlock));
vote(paraBlock);
return;
} // Of if
for (int i = 0; i < tempExpectedQueries; i++) {
if (numQuery >= maxNumQuery) {
System.out.println("No more queries are provided, numQuery = " + numQuery + ".");
vote(paraBlock);
return;
} // Of if
if (instanceStatusArray[paraBlock[i]] == 0) {
instanceStatusArray[paraBlock[i]] = 1;
predictedLabels[paraBlock[i]] = (int) dataset.instance(paraBlock[i]).classValue();
numQuery++;
} // Of if
} // Of for i
int tempFirstLabel = predictedLabels[paraBlock[0]];
boolean tempPure = true;
for (int i = 1; i < tempExpectedQueries; i++) {
if (predictedLabels[paraBlock[i]] != tempFirstLabel) {
tempPure = false;
break;
} // Of if
} // Of for i
if (tempPure) {
System.out.println("Classify for pure block: " + Arrays.toString(paraBlock));
for (int i = tempExpectedQueries; i < paraBlock.length; i++) {
if (instanceStatusArray[paraBlock[i]] == 0) {
predictedLabels[paraBlock[i]] = tempFirstLabel;
instanceStatusArray[paraBlock[i]] = 2;
} // Of if
} // Of for i
return;
} // Of if
int[][] tempBlocks = clusterInTwo(paraBlock);
for (int i = 0; i < 2; i++) {
clusterBasedActiveLearning(tempBlocks[i]);
} // Of for i
}// Of clusterBasedActiveLearning
public String toString() {
int[] tempStatusCounts = new int[3];
double tempCorrect = 0;
for (int i = 0; i < dataset.numInstances(); i++) {
tempStatusCounts[instanceStatusArray[i]]++;
if (predictedLabels[i] == (int) dataset.instance(i).classValue()) {
tempCorrect++;
} // Of if
} // Of for i
String resultString = "(unhandled, queried, classified) = "
+ Arrays.toString(tempStatusCounts);
resultString += "\r\nCorrect = " + tempCorrect + ", accuracy = "
+ (tempCorrect / dataset.numInstances());
return resultString;
}// Of toString
public static void main(String[] args) {
long tempStart = System.currentTimeMillis();
System.out.println("Starting ALEC.");
String arffFilename = "C:\\\\\\\\Users\\\\\\\\ASUS\\\\\\\\Desktop\\\\\\\\文件\\\\\\\\iris.arff";
Alec tempAlec = new Alec(arffFilename);
tempAlec.clusterBasedActiveLearning(0.15, 30, 3);
System.out.println(tempAlec);
long tempEnd = System.currentTimeMillis();
System.out.println("Runtime: " + (tempEnd - tempStart) + "ms.");
}// Of main
}// Of class Alec
运行截图：
扫一扫
303
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
