Using clustering to learn distance functions for supervised similarity assessment
Using clustering to learn distance functions for supervised similarity assessment
复制标题
DOI：
10.1016/j.engappai.2006.01.004
复制
发表时间：
2006-06-01
影响因子：
8
通讯作者：
Vilalta, R.
中科院分区：
文献类型：
--
作者：
Eick, Christoph F.;Rouhana, Alain;Vilalta, R.
评估对象之间的相似性是许多数据挖掘技术的前提。本文介绍了一种新的学习距离函数的方法，该方法最大化地对属于同一类的对象进行聚类。属于数据集的对象相对于给定的距离函数被聚类，然后通过权重调整启发式使用每个聚类的局部类密度信息来修改距离函数，从而在属性空间中增加类密度。重复该具有距离函数修改的交织聚类的过程，直到已经找到了“好的”距离函数。我们使用k-均值聚类算法实现了我们的方法。我们使用7个UCI数据集对传统的1-近邻(1-NN)分类器和压缩的1-NN分类器(称为NCC)进行了评估，NCC使用学习的距离函数和聚类质心而不是训练集的所有点。实验结果表明，与传统的1-NN分类器相比，属性加权显著提高了7个测试数据集中的2个的预测精度，而使用NCC显著提高了1-NN分类器对7个数据集中的4个的预测精度。(C)2006爱思唯尔有限公司。保留所有比赛。
Assessing the similarity between objects is a prerequisite for many data mining techniques. This paper introduces a novel approach to learn distance functions that maximizes the clustering of objects belonging to the same class. Objects belonging to a data set are clustered with respect to a given distance function and the local class density information of each cluster is then used by a weight adjustment heuristic to modify the distance function so that the class density is increased in the attribute space. This process of interleaving clustering with distance function modification is repeated until a "good" distance function has been found. We implemented our approach using the k-means clustering algorithm. We evaluated our approach using seven UCI data sets for a traditional 1-nearest-neighbor (1-NN) classifier and a compressed 1-NN classifier, called NCC, that uses the learnt distance function and cluster centroids instead of all the points of a training set. The experimental results show that attribute weighting leads to statistically significant improvements in prediction accuracy over a traditional 1-NN classifier for two of the seven data sets tested, whereas using NCC significantly improves the accuracy of the 1-NN classifier for four of the seven data sets. (C) 2006 Elsevier Ltd. All fights reserved.