Characterization measures of ensemble systems using a meta-learning approach

Abstract

In a decision making process, we are usually oriented to take into consideration all the relevant features (characteristics) involved in a specific problem. In Machine Learning, for instance, a decision is made through the use of a learning algorithm and the characterization process is represented by the corresponding datasets. In this context, classification algorithms can be applied, individually or through the use of ensemble systems (combination of classification methods), in the decision-making process. The concept of ensemble systems has emerged in the last decades as a strategy for combining independent classifiers (components), aiming to provide a decision that is potentially more effective than any single component. However, the design of the ensemble structure is not an easy task and it can have an important impact in the performance of these systems. In this paper, we investigate the use of meta-learning on the selection of the best configuration parameters (learning strategy, size and individual classifiers) for homogeneous structures of ensemble systems. The main aim of this analysis is to assess the effect of using meta-learning in the design of efficient and robust ensemble systems.

Transfer Learning for Synthetic Examples Selection in Meta-learning

“…Na literatura, diversos trabalhos têm investigado meta-aprendizagem de maneira mais profunda em tarefas de classificação e regressão e tem sido aplicadaà recomendação de algoritmos em uma gama de domínios de aplicações, como seleção de modelos de séries temporais [Prudêncio and Ludermir 2004] e medidas de caracterização de comitês [Parente et al 2013].…”

Automatic Recommendation Method for Classifier Ensemble Structure Using Meta-Learning

“…In the literature, several studies that use meta-learning to recommend algorithms can be found, such as in [15], [13], [16], [17] and [18]. However, although there are several relevant studies, it is clear that there is a lack of investigation towards the possibility of using recommendation methods to assist in effectively defining the main parameters of an ensemble, notably the classifier type, the number of classifiers and the combination methods.…”

An Empirical Analysis of Meta-learning for the Automatic Choice of Architecture and Components in Ensemble Systems

“…In the context of ensemble systems, very little effort has been done to use meta-learning as a recommendation tool in the automatic design of these systems [8], [9]. In [8], for instance, it is presented an approach to create customized model ensembles on demand, inspired by Lazy Learning.…”

“…It is important to emphasize that the approach proposed in [8] does not apply meta-learning on the recommendation level of configuration parameters for an ensemble system, unlike the methodology we apply in this paper. In addition, in [9], the authors combined the idea of meta-learning with ensemble systems, with the goal to help the design of efficient and robust ensemble systems. However, they recommended different parameters of an ensemble systems (size and structure) of the one we recommend in this paper (ensemble architecture and individual classifiers) and they used different metalearning methodology (meta-features and meta-learner).…”