Skip to main content

An extensive experimental evaluation of automated machine learning methods for recommending classification algorithms

Basgalupp, M.P., Barros, R.C., de Sá, A.G.C., Pappa, G.L., Mantovani, R.G., de Carvalho, A.C.P.L.F., Freitas, A.A. (2020) An extensive experimental evaluation of automated machine learning methods for recommending classification algorithms. Evolutionary Intelligence, . ISSN 1864-5909. E-ISSN 1864-5917. (doi:10.1007/s12065-020-00463-z) (Access to this publication is currently restricted. You may be able to access a copy if URLs are provided) (KAR id:82547)

PDF Author's Accepted Manuscript
Language: English

Restricted to Repository staff only until 19 August 2021.
Contact us about this Publication
[thumbnail of Evol-Intelligence-J-2020-Basgalupp-Subm-and-Accept.pdf]
Official URL
https://dx.doi.org/10.1007/s12065-020-00463-z

Abstract

This paper presents an experimental comparison among four automated machine learning (AutoML) methods for recommending the best classification algorithm for a given input dataset. Three of these methods are based on evolutionary algorithms (EAs), and the other is Auto-WEKA, a well-known AutoML method based on the combined algorithm selection and hyper-parameter optimisation (CASH) approach. The EA-based methods build classification algorithms from a single machine learning paradigm: either decision-tree induction, rule induction, or Bayesian network classification. Auto-WEKA combines algorithm selection and hyper-parameter optimisation to recommend classification algorithms from multiple paradigms. We performed controlled experiments where these four AutoML methods were given the same runtime limit for different values of this limit. In general, the difference in predictive accuracy of the three best AutoML methods was not statistically significant. However, the EA evolving decision-tree induction algorithms has the advantage of producing algorithms that generate interpretable classification models and that are more scalable to large datasets, by comparison with many algorithms from other learning paradigms that can be recommended by Auto-WEKA. We also observed that Auto-WEKA has shown meta-overfitting, a form of overfitting at the meta-learning level, rather than at the base-learning level.

Item Type: Article
DOI/Identification number: 10.1007/s12065-020-00463-z
Uncontrolled keywords: machine learning, data mining, classification, evolutionary algorithms
Subjects: Q Science > Q Science (General) > Q335 Artificial intelligence
Divisions: Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Computing
Depositing User: Alex Freitas
Date Deposited: 21 Aug 2020 21:54 UTC
Last Modified: 16 Feb 2021 14:14 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/82547 (The current URI for this page, for reference purposes)
Freitas, A.A.: https://orcid.org/0000-0001-9825-4700
  • Depositors only (login required):

Downloads

Downloads per month over past year