Results 1  10
of
184
Clustering with Bregman Divergences
 JOURNAL OF MACHINE LEARNING RESEARCH
, 2005
"... A wide variety of distortion functions are used for clustering, e.g., squared Euclidean distance, Mahalanobis distance and relative entropy. In this paper, we propose and analyze parametric hard and soft clustering algorithms based on a large class of distortion functions known as Bregman divergence ..."
Abstract

Cited by 309 (52 self)
 Add to MetaCart
A wide variety of distortion functions are used for clustering, e.g., squared Euclidean distance, Mahalanobis distance and relative entropy. In this paper, we propose and analyze parametric hard and soft clustering algorithms based on a large class of distortion functions known as Bregman divergences. The proposed algorithms unify centroidbased parametric clustering approaches, such as classical kmeans and informationtheoretic clustering, which arise by special choices of the Bregman divergence. The algorithms maintain the simplicity and scalability of the classical kmeans algorithm, while generalizing the basic idea to a very large class of clustering loss functions. There are two main contributions in this paper. First, we pose the hard clustering problem in terms of minimizing the loss in Bregman information, a quantity motivated by ratedistortion theory, and present an algorithm to minimize this loss. Secondly, we show an explicit bijection between Bregman divergences and exponential families. The bijection enables the development of an alternative interpretation of an ecient EM scheme for learning models involving mixtures of exponential distributions. This leads to a simple soft clustering algorithm for all Bregman divergences.
Efficient Clustering of HighDimensional Data Sets with Application to Reference Matching
, 2000
"... Many important problems involve clustering large datasets. Although naive implementations of clustering are computationally expensive, there are established efficient techniques for clustering when the dataset has either (1) a limited number of clusters, (2) a low feature dimensionality, or (3) a sm ..."
Abstract

Cited by 256 (12 self)
 Add to MetaCart
Many important problems involve clustering large datasets. Although naive implementations of clustering are computationally expensive, there are established efficient techniques for clustering when the dataset has either (1) a limited number of clusters, (2) a low feature dimensionality, or (3) a small number of data points. However, there has been much less work on methods of efficiently clustering datasets that are large in all three ways at oncefor example, having millions of data points that exist in many thousands of dimensions representing many thousands of clusters. We present a new technique for clustering these large, highdimensional datasets. The key idea involves using a cheap, approximate distance measure to efficiently divide the data into overlapping subsets we call canopies. Then clustering is performed by measuring exact distances only between points that occur in a common canopy. Using canopies, large clustering problems that were formerly impossible become practical. Under r...
InformationTheoretic CoClustering
 In KDD
, 2003
"... Twodimensional contingency or cooccurrence tables arise frequently in important applications such as text, weblog and marketbasket data analysis. A basic problem in contingency table analysis is coclustering: simultaneous clustering of the rows and columns. A novel theoretical formulation views ..."
Abstract

Cited by 249 (11 self)
 Add to MetaCart
Twodimensional contingency or cooccurrence tables arise frequently in important applications such as text, weblog and marketbasket data analysis. A basic problem in contingency table analysis is coclustering: simultaneous clustering of the rows and columns. A novel theoretical formulation views the contingency table as an empirical joint probability distribution of two discrete random variables and poses the coclustering problem as an optimization problem in information theory  the optimal coclustering maximizes the mutual information between the clustered random variables subject to constraints on the number of row and column clusters.
Survey of clustering data mining techniques
, 2002
"... Accrue Software, Inc. Clustering is a division of data into groups of similar objects. Representing the data by fewer clusters necessarily loses certain fine details, but achieves simplification. It models data by its clusters. Data modeling puts clustering in a historical perspective rooted in math ..."
Abstract

Cited by 247 (0 self)
 Add to MetaCart
Accrue Software, Inc. Clustering is a division of data into groups of similar objects. Representing the data by fewer clusters necessarily loses certain fine details, but achieves simplification. It models data by its clusters. Data modeling puts clustering in a historical perspective rooted in mathematics, statistics, and numerical analysis. From a machine learning perspective clusters correspond to hidden patterns, the search for clusters is unsupervised learning, and the resulting system represents a data concept. From a practical perspective clustering plays an outstanding role in data mining applications such as scientific data exploration, information retrieval and text mining, spatial database applications, Web analysis, CRM, marketing, medical diagnostics, computational biology, and many others. Clustering is the subject of active research in several fields such as statistics, pattern recognition, and machine learning. This survey focuses on clustering in data mining. Data mining adds to clustering the complications of very large datasets with very many attributes of different types. This imposes unique
Approximation Algorithms for Projective Clustering
 Proceedings of the ACM SIGMOD International Conference on Management of data, Philadelphia
, 2000
"... We consider the following two instances of the projective clustering problem: Given a set S of n points in R d and an integer k ? 0; cover S by k hyperstrips (resp. hypercylinders) so that the maximum width of a hyperstrip (resp., the maximum diameter of a hypercylinder) is minimized. Let w ..."
Abstract

Cited by 245 (21 self)
 Add to MetaCart
We consider the following two instances of the projective clustering problem: Given a set S of n points in R d and an integer k ? 0; cover S by k hyperstrips (resp. hypercylinders) so that the maximum width of a hyperstrip (resp., the maximum diameter of a hypercylinder) is minimized. Let w be the smallest value so that S can be covered by k hyperstrips (resp. hypercylinders), each of width (resp. diameter) at most w : In the plane, the two problems are equivalent. It is NPHard to compute k planar strips of width even at most Cw ; for any constant C ? 0 [50]. This paper contains four main results related to projective clustering: (i) For d = 2, we present a randomized algorithm that computes O(k log k) strips of width at most 6w that cover S. Its expected running time is O(nk 2 log 4 n) if k 2 log k n; it also works for larger values of k, but then the expected running time is O(n 2=3 k 8=3 log 4 n). We also propose another algorithm that computes a c...
A Framework for Clustering Evolving Data Streams
 In VLDB
, 2003
"... The clustering problem is a difficult problem for the data stream domain. This is because the large volumes of data arriving in a stream renders most traditional algorithms too inefficient. In recent years, a... ..."
Abstract

Cited by 239 (32 self)
 Add to MetaCart
The clustering problem is a difficult problem for the data stream domain. This is because the large volumes of data arriving in a stream renders most traditional algorithms too inefficient. In recent years, a...
Refining Initial Points for KMeans Clustering
, 1998
"... Practical approaches to clustering use an iterative procedure (e.g. KMeans, EM) which converges to one of numerous local minima. It is known that these iterative techniques are especially sensitive to initial starting conditions. We present a procedure for computing a refined starting condition fro ..."
Abstract

Cited by 232 (5 self)
 Add to MetaCart
Practical approaches to clustering use an iterative procedure (e.g. KMeans, EM) which converges to one of numerous local minima. It is known that these iterative techniques are especially sensitive to initial starting conditions. We present a procedure for computing a refined starting condition from a given initial one that is based on an efficient technique for estimating the modes of a distribution. The refined initial starting condition allows the iterative algorithm to converge to a "better" local minimum. The procedure is applicable to a wide class of clustering algorithms for both discrete and continuous data. We demonstrate the application of this method to the popular KMeans clustering algorithm and show that refined initial starting points indeed lead to improved solutions. Refinement run time is considerably lower than the time required to cluster the full database. The method is scalable and can be coupled with a scalable clustering algorithm to address the largescale cl...
Survey of clustering algorithms
 IEEE TRANSACTIONS ON NEURAL NETWORKS
, 2005
"... Data analysis plays an indispensable role for understanding various phenomena. Cluster analysis, primitive exploration with little or no prior knowledge, consists of research developed across a wide variety of communities. The diversity, on one hand, equips us with many tools. On the other hand, the ..."
Abstract

Cited by 230 (3 self)
 Add to MetaCart
Data analysis plays an indispensable role for understanding various phenomena. Cluster analysis, primitive exploration with little or no prior knowledge, consists of research developed across a wide variety of communities. The diversity, on one hand, equips us with many tools. On the other hand, the profusion of options causes confusion. We survey clustering algorithms for data sets appearing in statistics, computer science, and machine learning, and illustrate their applications in some benchmark data sets, the traveling salesman problem, and bioinformatics, a new field attracting intensive efforts. Several tightly related topics, proximity measure, and cluster validation, are also discussed.
CHAMELEON: A Hierarchical Clustering Algorithm Using Dynamic Modeling
, 1999
"... Clustering in data mining is a discovery process that groups a set of data such that the intracluster similarity is maximized and the intercluster similarity is minimized. Existing clustering algorithms, such as Kmeans, PAM, CLARANS, DBSCAN, CURE, and ROCK are designed to find clusters that fit s ..."
Abstract

Cited by 211 (23 self)
 Add to MetaCart
Clustering in data mining is a discovery process that groups a set of data such that the intracluster similarity is maximized and the intercluster similarity is minimized. Existing clustering algorithms, such as Kmeans, PAM, CLARANS, DBSCAN, CURE, and ROCK are designed to find clusters that fit some static models. These algorithms can breakdown if the choice of parameters in the static model is incorrect with respect to the data set being clustered, or if the model is not adequate to capture the characteristics of clusters. Furthermore, most of these algorithms breakdown when the data consists of clusters that are of diverse shapes, densities, and sizes. In this paper, we present a novel hierarchical clustering algorithm called CHAMELEON that measures the similarity of two clusters based on a dynamic model. In the clustering process, two clusters are merged only if the interconnectivity and closeness (proximity) between two clusters are high relative to the internal intercon...
Entropybased Subspace Clustering for Mining Numerical Data
, 1999
"... Mining numerical data is a relatively difficult problem in data mining. Clustering is one of the techniques. We consider a database with numerical attributes, in which each transaction is viewed as a multidimensional vector. By studying the clusters formed by these vectors, we can discover certain ..."
Abstract

Cited by 108 (1 self)
 Add to MetaCart
Mining numerical data is a relatively difficult problem in data mining. Clustering is one of the techniques. We consider a database with numerical attributes, in which each transaction is viewed as a multidimensional vector. By studying the clusters formed by these vectors, we can discover certain behaviors hidden in the data. Traditional clustering algorithms find clusters in the full space of the data sets. This results in high dimensional clusters, which are poorly comprehensible to human. One important task in this setting is the ability to discover clusters embedded in the subspaces of a highdimensional data set. This problem is known as subspace clustering. We follow the basic assumptions of previous work CLIQUE. It is found that the number of subspaces with clustering is very large, and a criterion called the coverage is proposed in CLIQUE for the pruning. In addition to coverage, we identify new useful criteria for this problem and propose an entropybased algorithm called ENC...