Selecting Machine Learning Algorithms Using the Ranking Meta-Learning Approach

Prudêncio, Ricardo B. C.; Souto, Michael Vandesteen Silva; Ludermir, Teresa B.

doi:10.1007/978-3-642-20980-2_7

Cited by 20 publications

(6 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We conducted our experiments on k = 3, meaning we may have a very different result if k is assigned to a different number. The conclusion obtained is the same result revealed by Prudancio et al (2011) and Chao et al (2020). where K-NN as a meta-learner is used for a small number of meta examples and a large number of meta examples (some of them generated by using datasetoids, comparing the results of both shows that K-NN as meta-learner has better performance when the number of examples is small as K-NN is sensitive to the irrelevant meta examples potentially produced by datasetoids.…”

Section: Resultssupporting

confidence: 92%

Cost-sensitive meta-learning framework

Shilbayeh

Vadera

2021

JM2

View full text Add to dashboard Cite

Purpose This paper aims to describe the use of a meta-learning framework for recommending cost-sensitive classification methods with the aim of answering an important question that arises in machine learning, namely, “Among all the available classification algorithms, and in considering a specific type of data and cost, which is the best algorithm for my problem?” Design/methodology/approach This paper describes the use of a meta-learning framework for recommending cost-sensitive classification methods for the aim of answering an important question that arises in machine learning, namely, “Among all the available classification algorithms, and in considering a specific type of data and cost, which is the best algorithm for my problem?” The framework is based on the idea of applying machine learning techniques to discover knowledge about the performance of different machine learning algorithms. It includes components that repeatedly apply different classification methods on data sets and measures their performance. The characteristics of the data sets, combined with the algorithms and the performance provide the training examples. A decision tree algorithm is applied to the training examples to induce the knowledge, which can then be used to recommend algorithms for new data sets. The paper makes a contribution to both meta-learning and cost-sensitive machine learning approaches. Those both fields are not new, however, building a recommender that recommends the optimal case-sensitive approach for a given data problem is the contribution. The proposed solution is implemented in WEKA and evaluated by applying it on different data sets and comparing the results with existing studies available in the literature. The results show that a developed meta-learning solution produces better results than METAL, a well-known meta-learning system. The developed solution takes the misclassification cost into consideration during the learning process, which is not available in the compared project. Findings The proposed solution is implemented in WEKA and evaluated by applying it to different data sets and comparing the results with existing studies available in the literature. The results show that a developed meta-learning solution produces better results than METAL, a well-known meta-learning system. Originality/value The paper presents a major piece of new information in writing for the first time. Meta-learning work has been done before but this paper presents a new meta-learning framework that is costs sensitive.

show abstract

Section: Resultssupporting

confidence: 92%

Cost-sensitive meta-learning framework

Shilbayeh

Vadera

2021

JM2

View full text Add to dashboard Cite

show abstract

“…Similarly, in [37], developers defined 32 meta-examples (each one corresponding to a dataset) described by a set of meta-features for a gene expression dataset, and a vector with the ranking of the clustering algorithms for that dataset. To measure the similarity between meta-features, they used Euclidean distance, Pearson correlation and cosine.…”

Section: Review On Algorithm Selection Using Meta-learningmentioning

confidence: 99%

QoS-based data analytic service selection: a comparative study of different learning models

Alghofaily¹

2023

Preprint

View full text Add to dashboard Cite

QoS-based web service selection has been studied in the service computing community for some time; however, data characteristics are not considered. In this work, we have studied the use of different machine learning algorithms as meta-learners in predicting the performance of data analytic services for the given dataset. We used a meta-learning algorithm to incorporate meta-features in the selection process and we used clustering services as an example of data analytic services. We have also investigated the impact of the number of data features on the performance of the meta-learners. We found that, out of the 5 classification models, SVM showed the best results in predicting the recommended service for the given dataset with an accuracy of 78%. When it comes to regression models, MLP was the best regressor. We recommend considering only simple meta-features that can be collected for most datasets, as those proved to be sufficient to achieve good prediction accuracy.

show abstract

“…Later Nakhaeizadeh and Schnabl (1997) , and later Keller et al (2000) , and Brazdil and Soares (2000) also adopted similar methods. In 2011, RBC Prudencio, MCPD Souto and TB Ludermir applied the ordering meta-learning method to the time series and gene expression data clustering field ( Prudêncio et al, 2011 ). In 2017, Finn et al introduced the theory of meta-learning in the fast adaptation study of deep networks ( Finn and Levine, 2017 ).…”

Section: Introductionmentioning

confidence: 99%

Research on eight machine learning algorithms applicability on different characteristics data sets in medical classification tasks

Zhang,

Li,

Xin

2024

Front. Comput. Neurosci.

View full text Add to dashboard Cite

With the vigorous development of data mining field, more and more algorithms have been proposed or improved. How to quickly select a data mining algorithm that is suitable for data sets in medical field is a challenge for some medical workers. The purpose of this paper is to study the comparative characteristics of the general medical data set and the general data sets in other fields, and find the applicability rules of the data mining algorithm suitable for the characteristics of the current research data set. The study quantified characteristics of the research data set with 26 indicators, including simple indicators, statistical indicators and information theory indicators. Eight machine learning algorithms with high maturity, low user involvement and strong family representation were selected as the base algorithms. The algorithm performances were evaluated by three aspects: prediction accuracy, running speed and memory consumption. By constructing decision tree and stepwise regression model to learn the above metadata, the algorithm applicability knowledge of medical data set is obtained. Through cross-verification, the accuracy of all the algorithm applicability prediction models is above 75%, which proves the validity and feasibility of the applicability knowledge.

show abstract

Selecting Machine Learning Algorithms Using the Ranking Meta-Learning Approach

Cited by 20 publications

References 35 publications

Cost-sensitive meta-learning framework

Cost-sensitive meta-learning framework

QoS-based data analytic service selection: a comparative study of different learning models

Research on eight machine learning algorithms applicability on different characteristics data sets in medical classification tasks

Contact Info

Product

Resources

About