Details
| Original language | English |
|---|---|
| Pages (from-to) | 1253-1286 |
| Number of pages | 34 |
| Journal | Machine learning |
| Volume | 112 |
| Issue number | 4 |
| Early online date | 18 Apr 2022 |
| Publication status | Published - Apr 2023 |
| Externally published | Yes |
Abstract
The problem of selecting an algorithm that appears most suitable for a specific instance of an algorithmic problem class, such as the Boolean satisfiability problem, is called instance-specific algorithm selection. Over the past decade, the problem has received considerable attention, resulting in a number of different methods for algorithm selection. Although most of these methods are based on machine learning, surprisingly little work has been done on meta learning, that is, on taking advantage of the complementarity of existing algorithm selection methods in order to combine them into a single superior algorithm selector. In this paper, we introduce the problem of meta algorithm selection, which essentially asks for the best way to combine a given set of algorithm selectors. We present a general methodological framework for meta algorithm selection as well as several concrete learning methods as instantiations of this framework, essentially combining ideas of meta learning and ensemble learning. In an extensive experimental evaluation, we demonstrate that ensembles of algorithm selectors can significantly outperform single algorithm selectors and have the potential to form the new state of the art in algorithm selection.
Keywords
- Algorithm selection, Bagging, Boosting, Ensemble learning, Meta learning, Stacking
ASJC Scopus subject areas
- Computer Science(all)
- Software
- Computer Science(all)
- Artificial Intelligence
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Machine learning, Vol. 112, No. 4, 04.2023, p. 1253-1286.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Algorithm selection on a meta level
AU - Tornede, Alexander
AU - Gehring, Lukas
AU - Tornede, Tanja
AU - Wever, Marcel
AU - Hüllermeier, Eyke
N1 - Publisher Copyright: © 2022, The Author(s).
PY - 2023/4
Y1 - 2023/4
N2 - The problem of selecting an algorithm that appears most suitable for a specific instance of an algorithmic problem class, such as the Boolean satisfiability problem, is called instance-specific algorithm selection. Over the past decade, the problem has received considerable attention, resulting in a number of different methods for algorithm selection. Although most of these methods are based on machine learning, surprisingly little work has been done on meta learning, that is, on taking advantage of the complementarity of existing algorithm selection methods in order to combine them into a single superior algorithm selector. In this paper, we introduce the problem of meta algorithm selection, which essentially asks for the best way to combine a given set of algorithm selectors. We present a general methodological framework for meta algorithm selection as well as several concrete learning methods as instantiations of this framework, essentially combining ideas of meta learning and ensemble learning. In an extensive experimental evaluation, we demonstrate that ensembles of algorithm selectors can significantly outperform single algorithm selectors and have the potential to form the new state of the art in algorithm selection.
AB - The problem of selecting an algorithm that appears most suitable for a specific instance of an algorithmic problem class, such as the Boolean satisfiability problem, is called instance-specific algorithm selection. Over the past decade, the problem has received considerable attention, resulting in a number of different methods for algorithm selection. Although most of these methods are based on machine learning, surprisingly little work has been done on meta learning, that is, on taking advantage of the complementarity of existing algorithm selection methods in order to combine them into a single superior algorithm selector. In this paper, we introduce the problem of meta algorithm selection, which essentially asks for the best way to combine a given set of algorithm selectors. We present a general methodological framework for meta algorithm selection as well as several concrete learning methods as instantiations of this framework, essentially combining ideas of meta learning and ensemble learning. In an extensive experimental evaluation, we demonstrate that ensembles of algorithm selectors can significantly outperform single algorithm selectors and have the potential to form the new state of the art in algorithm selection.
KW - Algorithm selection
KW - Bagging
KW - Boosting
KW - Ensemble learning
KW - Meta learning
KW - Stacking
UR - http://www.scopus.com/inward/record.url?scp=85128259652&partnerID=8YFLogxK
U2 - 10.1007/s10994-022-06161-4
DO - 10.1007/s10994-022-06161-4
M3 - Article
VL - 112
SP - 1253
EP - 1286
JO - Machine learning
JF - Machine learning
SN - 0885-6125
IS - 4
ER -