Using diversity in cluster ensembles

Kuncheva, Ludmila I.; Hadjitodorov, Stefan

doi:10.1109/icsmc.2004.1399790

Cited by 189 publications

(145 citation statements)

References 8 publications

Supporting

Mentioning

143

Contrasting

Order By: Relevance

“…The normalized mutual information (NMI) [35] was used to assess the similarity between a couple of community partitions. For two networks with partitions, respectively, and , it is defined as…”

Section: Statistical Analysis Of Modularitymentioning

confidence: 99%

A Novel Synchronization-Based Approach for Functional Connectivity Analysis

et al. 2017

View full text Add to dashboard Cite

Complex network analysis has become a gold standard to investigate functional connectivity in the human brain. Popular approaches for quantifying functional coupling between fMRI time series are linear zero-lag correlation methods; however, they might reveal only partial aspects of the functional links between brain areas. In this work, we propose a novel approach for assessing functional coupling between fMRI time series and constructing functional brain networks. A phase space framework is used to map couples of signals exploiting their cross recurrence plots (CRPs) to compare the trajectories of the interacting systems. A synchronization metric is extracted from the CRP to assess the coupling behavior of the time series. Since the functional communities of a healthy population are expected to be highly consistent for the same task, we defined functional networks of taskrelated fMRI data of a cohort of healthy subjects and applied a modularity algorithm in order to determine the community structures of the networks. The within-group similarity of communities is evaluated to verify whether such new metric is robust enough against noise. The synchronization metric is also compared with Pearson's correlation coefficient and the detected communities seem to better reflect the functional brain organization during the specific task.

show abstract

Section: Statistical Analysis Of Modularitymentioning

confidence: 99%

A Novel Synchronization-Based Approach for Functional Connectivity Analysis

et al. 2017

View full text Add to dashboard Cite

show abstract

“…The clusterings produced by kmeans are mapped into a co-association matrix, which measures the similarity between the samples. Kuncheva et al [13] extend the work in [8] by choosing at random the number of clusters for each ensemble member. The authors in [16] introduce a meta-clustering procedure: first, each clustering is mapped into a distance matrix; second, the multiple distance matrices are combined, and a hierarchical clustering method is introduced to compute a consensus clustering.…”

Section: Related Workmentioning

confidence: 99%

Weighted Clustering Ensembles

Al-Razgan¹,

Domeniconi²

2006

Proceedings of the 2006 SIAM International Conference on Data Mining

View full text Add to dashboard Cite

Cluster ensembles offer a solution to challenges inherent to clustering arising from its ill-posed nature. Cluster ensembles can provide robust and stable solutions by leveraging the consensus across multiple clustering results, while averaging out emergent spurious structures that arise due to the various biases to which each participating algorithm is tuned. In this paper, we address the problem of combining multiple weighted clusters which belong to different subspaces of the input space. We leverage the diversity of the input clusterings in order to generate a consensus partition that is superior to the participating ones. Since we are dealing with weighted clusters, our consensus function makes use of the weight vectors associated with the clusters. The experimental results show that our ensemble technique is capable of producing a partition that is as good as or better than the best individual clustering.

show abstract

“…Diverse partitions are typically generated by using different clustering algorithms [1], or by applying a single algorithm with different parameter settings [10,16,17], possibly in combination with data or feature sampling [30,9,20,29].…”

Section: Related Workmentioning

confidence: 99%

Nonparametric Bayesian Clustering Ensembles

Wang

Domeniconi

Laskey³

2010

Machine Learning and Knowledge Discovery in Databases

View full text Add to dashboard Cite

Abstract. Forming consensus clusters from multiple input clusterings can improve accuracy and robustness. Current clustering ensemble methods require specifying the number of consensus clusters. A poor choice can lead to under or over fitting. This paper proposes a nonparametric Bayesian clustering ensemble (NBCE) method, which can discover the number of clusters in the consensus clustering. Three inference methods are considered: collapsed Gibbs sampling, variational Bayesian inference, and collapsed variational Bayesian inference. Comparison of NBCE with several other algorithms demonstrates its versatility and superior stability.

show abstract

Using diversity in cluster ensembles

Cited by 189 publications

References 8 publications

A Novel Synchronization-Based Approach for Functional Connectivity Analysis

A Novel Synchronization-Based Approach for Functional Connectivity Analysis

Weighted Clustering Ensembles

Nonparametric Bayesian Clustering Ensembles

Contact Info

Product

Resources

About