Consensus clustering

Consensus clustering

Clustering is the assignment of objects into groups (called clusters) so that objects from the same cluster are more similar to each other than objects from different clusters. Often similarity is assessed according to a distance measure. Clustering is a common technique for statistical data analysis, which is used in many fields, including machine learning, data mining, pattern recognition, image analysis and bioinformatics.

Consensus clustering has emerged as an important elaboration of the classical clustering problem. Consensus clustering, also called aggregation of clustering (or partitions), refers to the situation in which a number of different (input) clusterings have been obtained for a particular dataset and it is desired to find a single (consensus) clustering which is a better fit in some sense than the existing clusterings. Consensus clustering is thus the problem of reconciling clustering information about the same data set coming from different sources or from different runs of the same algorithm. When cast as an optimization problem, consensus clustering is known as median partition, and has been shown to be NP-complete. Consensus clustering for unsupervised learning is analogous to ensemble learning in supervised learning.

Contents

Issues with existing clustering techniques

  • Current clustering techniques do not address all the requirements adequately.
  • Dealing with large number of dimensions and large number of data items can be problematic because of time complexity;
  • Effectiveness of the method depends on the definition of “distance” (for distance based clustering)
  • If an obvious distance measure doesn’t exist we must “define” it, which is not always easy, especially in multidimensional spaces.
  • The result of the clustering algorithm (that in many cases can be arbitrary itself) can be interpreted in different ways.

Why Consensus Clustering?

  • There are potential shortcomings for each of the known clustering techniques.
  • Interpretation of results are difficult in a few cases.
  • When there is no knowledge about the number of clusters, it becomes difficult.
  • They are extremely sensitive to the initial settings.
  • Some algorithms can never undo what was done previously.
  • Iterative descent clustering methods, such as the SOM and K-Means clustering circumvent some of the shortcomings of Hierarchical clustering by providing for univocally defined clusters and cluster boundaries. However, they lack the intuitive and visual appeal of Hierarchical clustering, and the number of clusters must be chosen a priori.
  • An extremely important issue in cluster analysis is the validation of the clustering results, that is, how to gain confidence about the significance of the clusters provided by the clustering technique, (cluster numbers and cluster assignments). Lacking an external objective criterion (the equivalent of a known class label in supervised learning) this validation becomes somewhat elusive.

Advantages of Consensus Clustering

  • Provides for a method to represent the consensus across multiple runs of a clustering algorithm, to determine the number of clusters in the data, and to assess the stability of the discovered clusters.
  • The method can also be used to represent the consensus over multiple runs of a clustering algorithm with random restart (such as K-means, model-based Bayesian clustering, SOM, etc.), so as to account for * its sensitivity to the initial conditions.
  • It also provides for a visualization tool to inspect cluster number, membership, and boundaries.
  • We will be able to extract lot of features / attributes from multiples runs of different clustering algorithms on the data. These features can give us valuable information in doing a final consensus clustering.

Related Work

1. Clustering Ensemble (Strehl and Ghosh): They consider various formulations for the problem, most of which reduce the problem to a hyper-graph partitioning problem. In one of their formulations they consider the same graph as in the correlation clustering problem. The solution they propose is to compute the best k-partition of the graph, which does not take into account the penalty for merging two nodes that are far apart.

2. Clustering Aggregation (Fern and Brodley): They apply the clustering aggregation idea to a collection of soft clusterings they obtain by random projections. They use an agglomerative algorithm and do not penalize for merging dissimilar nodes.

3. Fred and Jain: propose to use a single linkage algorithm to combine multiple runs of the k-means algorithm.

4. Dana Cristofor and Dan Simovici: observe the connection between clustering aggregation and clustering of categorical data. They propose information theoretic distance measures, and they propose genetic algorithms for finding the best aggregation solution.

5. Topchy et al.: They define clustering aggregation as a maximum likelihood estimation problem, and they propose an EM algorithm for finding the consensus clustering.

Hard Ensemble Clustering

This approach by Strehl and Ghosh introduces the problem of combining multiple partitionings of a set of objects into a single consolidated clustering without accessing the features or algorithms that determined these partitionings. They discuss three approaches towards solving this problem to obtain high quality consensus functions. Their techniques have low computational costs and this makes it feasible to evaluate each of the techniques discussed below and arrive at the best solution by comparing the results against the objective function.

Efficient Consensus Functions

1. Cluster-based Similarity Partitioning Algorithm (CSPA)

In CSPA the similarity between two data-points is defined to be directly proportional to number of constituent clusterings of the ensemble in which they are clustered together. The intuition is that the more similar two data-points are the higher is the chance that constituent clusterings will place them in the same cluster. CSPA is the simplest heuristic, but its computational and storage complexity are both quadratic in n. The following two methods are computationally less expensive:

2. Hyper-Graph Partitioning Algorithm (HGPA)

The HGPA algorithm takes a very different approach to finding the consensus clustering than the previous method. The cluster ensemble problem is formulated as partitioning the hypergraph by cutting a minimal number of hyperedges. They make use of hMETIS which is a hypergraph partitioning package system.

3. Meta-CLustering Algorithm (MCLA)

The Meta-CLustering Algorithm (MCLA) is based on clustering clusters. First, it tries to solve the cluster correspondence problem and then uses voting to place data-points into the final consensus clusters. The cluster correspondence problem is solved by grouping the clusters identified in the individual clusterings of the ensemble. The clustering is performed using METIS and Spectral clustering.


Soft Clustering Ensembles

Punera and Ghosh extended the idea of hard clustering ensembles to the soft clustering scenario. Each instance in a soft ensemble is represented by a concatenation of r posterior membership probability distributions obtained from the constituent clustering algorithms. We can define a distance measure between two instances using the Kullback-Leibler (KL) divergence, which calculates the “distance” between two probability distributions.

1. sCSPA

sCSPA extends CSPA by calculating a similarity matrix. Each object is visualized as a point in dimensional space, with each dimension corresponding to probability of its belonging to a cluster. This technique first transforms the objects into a label-space and then interprets the dot product between the vectors representing the objects as their similarity.

2. sMCLA

sMCLA extends MCLA by accepting soft clusterings as input. sMCLA’s working can be divided into the following steps:

  • Construct Soft Meta-Graph of Clusters
  • Group the Clusters into Meta-Clusters
  • Collapse Meta-Clusters using Weighting
  • Compete for Objects

3. sHBGF

HBGF represents the ensemble as a bipartite graph with clusters and instances as nodes, and edges between the instances and the clusters they belong to[1]. This approach can be trivially adapted to consider soft ensembles since the graph partitioning algorithm METIS accepts weights on the edges of the graph to be partitioned. In sHBGF, the graph has n + t vertices, where t is the total number of underlying clusters.

  1. ^ Solving cluster ensemble problems by bipartite graph partitioning, Xiaoli Zhang Fern and Carla E. Brodley,Proceedings of the twenty-first international conference on Machine learning

References

Further reading


Wikimedia Foundation. 2010.

Игры ⚽ Поможем написать реферат

Look at other dictionaries:

  • Cluster analysis — The result of a cluster analysis shown as the coloring of the squares into three clusters. Cluster analysis or clustering is the task of assigning a set of objects into groups (called clusters) so that the objects in the same cluster are more… …   Wikipedia

  • cosmos — /koz meuhs, mohs/, n., pl. cosmos, cosmoses for 2, 4. 1. the world or universe regarded as an orderly, harmonious system. 2. a complete, orderly, harmonious system. 3. order; harmony. 4. any composite plant of the genus Cosmos, of tropical… …   Universalium

  • Collaborative method — Collaborative methods are processes, behaviors and conversations that relate to collaboration between individuals.[1] These methods specifically aim to increase the success of teams as they engage in collaborative problem solving. Forms, rubrics …   Wikipedia

  • United States — a republic in the N Western Hemisphere comprising 48 conterminous states, the District of Columbia, and Alaska in North America, and Hawaii in the N Pacific. 267,954,767; conterminous United States, 3,022,387 sq. mi. (7,827,982 sq. km); with… …   Universalium

  • Race (classification of humans) — Race Classification Race (classification of humans) Genetics …   Wikipedia

  • Drug design — Not to be confused with Designer drug. Drug design, also sometimes referred to as rational drug design or structure based drug design, is the inventive process of finding new medications based on the knowledge of the biological target.[1] The… …   Wikipedia

  • Glossaire du data mining — Exploration de données Articles principaux Exploration de données Fouille de données spatiales Fouille du web Fouille de flots de données Fouille de textes …   Wikipédia en Français

  • Quantitative comparative linguistics — is a branch of comparative linguistics that applies mathematical models to the problem of classifying language relatedness. This includes the use of computational phylogenetics and cladistics to define an optimal tree (or network) to represent a… …   Wikipedia

  • Nucleic acid structure prediction — This article is about the computational prediction of nucleic acid structure. For experimental methods, see Nucleic acid structure determination. Nucleic acid structure prediction is a computational method to determine nucleic acid secondary and… …   Wikipedia

  • Sound symbolism — or phonosemantics is a branch of linguistics and refers to the idea that vocal sounds have meaning. In particular, sound symbolism is the idea that phonemes (the written representations of sounds, transcribed between slashes like this: /b/) carry …   Wikipedia

Share the article and excerpts

Direct link
Do a right-click on the link above
and select “Copy Link”