A survey of cluster validity indices for automatic data clustering using differential evolution

José-García, Adán; Gómez-Flores, Wilfrido

doi:10.1145/3449639.3459341

Cited by 18 publications

(11 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although no consensus exists regarding those properties, most definitions agree that the fundamental characteristics of clusters are homogeneity (compactness) within and heterogeneity (separation) across groups. Many clustering criteria have been proposed [3], [4], each evaluating, in particular ways, one of these properties or a combination of them. It is unlikely, however, that a single solution can simultaneously optimize all the desirable, but usually conflicting, characteristics [5].…”

Section: A Multi-objective Clusteringmentioning

confidence: 99%

Evolutionary Multiobjective Clustering Over Multiple Conflicting Data Views

Garza-Fabre

Handl

José-García

2023

IEEE Trans. Evol. Computat.

View full text Add to dashboard Cite

Multi-view data analysis provides an effective means to integrate the distinct information sources which are inherent to many applications. Data clustering in a multi-view setting specifically aims to identify the most appropriate grouping for a collection of entities, where those entities (or their relationships) can be described from multiple perspectives. Leveraging recent advances in multi-objective clustering, we propose a new evolutionary method to tackle this challenge. Designed around a flexible and unbiased solution representation, together with strategies based on the minimum spanning tree and neighborhood relations, our algorithm optimizes multiple objectives simultaneously to effectively explore the space of candidate trade-offs between the data views. Through a series of experiments, we investigate the suitability of our proposal in the context of a bioinformatics application, clustering of plausible protein structures, and a diverse set of synthetic problems. The specific case of two data views is considered in this paper. The evaluation with respect to a variety of reference approaches demonstrates the effectiveness of our method in discovering high-quality partitions in a multiview setting. Robustness against unreliable data sources and the ability to automatically determine the number of clusters, are additional advantages evidenced by the results obtained.

show abstract

Section: A Multi-objective Clusteringmentioning

confidence: 99%

Evolutionary Multiobjective Clustering Over Multiple Conflicting Data Views

Garza-Fabre

Handl

José-García

2023

IEEE Trans. Evol. Computat.

View full text Add to dashboard Cite

show abstract

“…Researchers associated with the CRIStAL Laboratory of the University of Lille, France have implemented a CVI package in the MATLAB programming language for the reproducibility of a survey of CVIs (José-Garcıá, 2021;José-Garcıá & Gómez-Flores, 2021). This repository contains a large variety of CVIs from the literature, though they are lacking their incremental variants.…”

Section: Comparison To Existing Implementationsmentioning

confidence: 99%

ClusterValidityIndices.jl: Batch and Incremental Metrics for Unsupervised Learning

Petrenko¹,

Wunsch²

2022

JOSS

View full text Add to dashboard Cite

ClusterValidityIndices.jl is a Julia package for evaluating the performance of clustering algorithms without the aid of supervised labels. Cluster Validity Indices (CVI) provide a metric of the over-or under-partitioning of an arbitrary clustering algorithm with only the original data and labels assigned by the clustering algorithm. Furthermore, there exist formulations of every CVI such that they may run incrementally (i.e. Incremental CVIs, or ICVI), streaming alongside the clustering algorithm and producing the same results as in their batch implementations. Using a standard interface, each CVI in this package can be run with any clustering algorithm to produce a metric of that algorithm's performance in scenarios where explicit supervised labels do not exist, which is extremely useful in real-world applications where that is often the case.

show abstract

“…Thus, f needs to correctly evaluate the properties that determine a good partition, being responsible for guiding the search process towards high-quality solutions. Many criteria have been proposed so far [21], [22], each presenting a specific formulation to evaluate (either one or a combination of) properties such as intra-cluster homogeneity (compactness), connectedness, and inter-cluster separation. The diversity of existing clustering criteria highlights the lack of consensus on how to assess partition quality, and the fact that it is unlikely that a single solution can simultaneously satisfy all the desirable but (usually) conflicting properties [23].…”

Section: B Multiobjective Clusteringmentioning

confidence: 99%

Decision Making in Evolutionary Multiobjective Clustering: A Machine Learning Challenge

Garza-Fabre¹,

Sánchez-Martínez²,

Aldana-Bobadilla

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Evolutionary multiobjective algorithms have become a popular choice to tackle the clustering problem. On the one hand, the simultaneous optimization of complementary clustering criteria offers an increased robustness to changes in data characteristics. On the other hand, the evolutionary search is able to approximate the Pareto optimal front and deliver a set of trade-offs between these criteria in a single algorithm execution. Decision making is the concluding stage of the pipeline, having as its goal the selection of a single, final solution from the set of candidate trade-offs produced. This is a complex task for which a definitive answer does not seem to be available, as the underlying assumptions of existing techniques may not hold for all applications. In this paper, we investigate an alternative approach to address this challenge: posing it as a learning problem. The key idea is to build a model that, given a proper characterization of solutions and their context (defined by the full approximation solution set and the specific clustering task at hand), is able to estimate quality and facilitate the identification of the best choice. To evaluate the suitability of this approach, we conduct a series of experiments over diverse synthetic and real-world datasets, including comparisons against a range of representative decision-making strategies from the literature. Our proposal exhibits greater flexibility in dealing with problems of varying characteristics, consistently outperforming the reference methods considered. This study demonstrates that it is possible to learn from the decisionmaking process in example settings and generalize the acquired knowledge to new scenarios.

show abstract

A survey of cluster validity indices for automatic data clustering using differential evolution

Cited by 18 publications

References 39 publications

Evolutionary Multiobjective Clustering Over Multiple Conflicting Data Views

Evolutionary Multiobjective Clustering Over Multiple Conflicting Data Views

ClusterValidityIndices.jl: Batch and Incremental Metrics for Unsupervised Learning

Decision Making in Evolutionary Multiobjective Clustering: A Machine Learning Challenge

Contact Info

Product

Resources

About