Boosting for Model-Based Data Clustering

Saffari, Amir; Bischof, Horst

doi:10.1007/978-3-540-69321-5_6

Cited by 4 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Correspondingly, the loss of consensus partition can be formulated as the weighted average of the loss produced from the input partitions {P t } T t =1 [48], [50] …”

Section: A Hybrid Samplingmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid Sampling-Based Clustering Ensemble With Global and Local Constitutions

Yang

Jiang

2016

IEEE Trans. Neural Netw. Learning Syst.

111

View full text Add to dashboard Cite

Among a number of ensemble learning techniques, boosting and bagging are the most popular sampling-based ensemble approaches for classification problems. Boosting is considered stronger than bagging on noise-free data set with complex class structures, whereas bagging is more robust than boosting in cases where noise data are present. In this paper, we extend both ensemble approaches to clustering tasks, and propose a novel hybrid sampling-based clustering ensemble by combining the strengths of boosting and bagging. In our approach, the input partitions are iteratively generated via a hybrid process inspired by both boosting and bagging. Then, a novel consensus function is proposed to encode the local and global cluster structure of input partitions into a single representation, and applies a single clustering algorithm to such representation to obtain the consolidated consensus partition. Our approach has been evaluated on 2-D-synthetic data, collection of benchmarks, and real-world facial recognition data sets, which show that the proposed technique outperforms the existing benchmarks for a variety of clustering tasks.

show abstract

“…Correspondingly, the loss of consensus partition can be formulated as the weighted average of the loss produced from the input partitions {P t } T t =1 [48], [50] …”

Section: A Hybrid Samplingmentioning

confidence: 99%

“…To derive the loss function for our proposed clustering ensemble, we convert L E N to an exponential form as described in (5) based on Jensen's inequality for the convex exponential transformation [50] …”

Section: A Hybrid Samplingmentioning

confidence: 99%

Hybrid Sampling-Based Clustering Ensemble With Global and Local Constitutions

Yang

Jiang

2016

IEEE Trans. Neural Netw. Learning Syst.

111

View full text Add to dashboard Cite

show abstract

“…The CSPA is applied on the final similarity matrix S to obtain the consensus clustering. Saffari and Bischof (2008) combine the boosting framework with model-based clustering. In the mth boosting iteration, the base clustering C m is obtaining by minimizing the loss 1 n ∑ n i=1 w i ∑ k r=1 Pr(x x x i belongs to the rth cluster|C m ) (x x x i , r|C m ), where (x x x i , r|C m ) is the loss for assigning object x x x i to the rth cluster.…”

Section: Weighting Objectsmentioning

confidence: 99%

Weighted Clustering Ensemble: A Review

Zhang

2019

Preprint

View full text Add to dashboard Cite

Clustering ensemble has emerged as a powerful tool for improving both the robustness and the stability of results from individual clustering methods. Weighted clustering ensemble arises naturally from clustering ensemble. One of the arguments for weighted clustering ensemble is that elements (clusterings or clusters) in a clustering ensemble are of different quality, or that objects or features are of varying significance. However, it is not possible to directly apply the weighting mechanisms from classification (supervised) domain to clustering (unsupervised) domain, also because clustering is inherently an ill-posed problem. This paper provides an overview of weighted clustering ensemble by discussing different types of weights, major approaches to determining weight values, and applications of weighted clustering ensemble to complex data. The unifying framework presented in this paper will help clustering practitioners select the most appropriate weighting mechanisms for their own problems.

show abstract