Details
| Original language | English |
|---|---|
| Title of host publication | GECCO 2023 - Proceedings of the 2023 Genetic and Evolutionary Computation Conference |
| Pages | 597-605 |
| Number of pages | 9 |
| ISBN (electronic) | 9798400701191 |
| Publication status | Published - 2023 |
| Externally published | Yes |
Publication series
| Name | Proceedings of the Genetic and Evolutionary Computation Conference |
|---|
Abstract
In multi-class classification, it can be beneficial to decompose a learning problem into several simpler problems. One such reduction technique is the use of so-called nested dichotomies, which recursively bisect the set of possible classes such that the resulting subsets can be arranged in the form of a binary tree, where each split defines a binary classification problem. Recently, a genetic algorithm for optimizing the structure of such nested dichotomies has achieved state-of-The-Art results. Motivated by its success, we propose to extend this approach using a co-evolutionary scheme to optimize both the structure of nested dichotomies and their composition into ensembles through which they are evaluated. Furthermore, we present an experimental study showing this approach to yield ensembles of nested dichotomies at substantially lower cost and, in some cases, even with an improved generalization performance.
Keywords
- coevolution, nested dichotomy, supervised learning
ASJC Scopus subject areas
- Computer Science(all)
- Software
- Computer Science(all)
- Artificial Intelligence
- Mathematics(all)
- Theoretical Computer Science
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
GECCO 2023 - Proceedings of the 2023 Genetic and Evolutionary Computation Conference. 2023. p. 597-605 (Proceedings of the Genetic and Evolutionary Computation Conference).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Cooperative Co-Evolution for Ensembles of Nested Dichotomies for Multi-Class Classification.
AU - Wever, Marcel
AU - Özdogan, Miran
AU - Hüllermeier, Eyke
N1 - Publisher Copyright: © 2023 ACM.
PY - 2023
Y1 - 2023
N2 - In multi-class classification, it can be beneficial to decompose a learning problem into several simpler problems. One such reduction technique is the use of so-called nested dichotomies, which recursively bisect the set of possible classes such that the resulting subsets can be arranged in the form of a binary tree, where each split defines a binary classification problem. Recently, a genetic algorithm for optimizing the structure of such nested dichotomies has achieved state-of-The-Art results. Motivated by its success, we propose to extend this approach using a co-evolutionary scheme to optimize both the structure of nested dichotomies and their composition into ensembles through which they are evaluated. Furthermore, we present an experimental study showing this approach to yield ensembles of nested dichotomies at substantially lower cost and, in some cases, even with an improved generalization performance.
AB - In multi-class classification, it can be beneficial to decompose a learning problem into several simpler problems. One such reduction technique is the use of so-called nested dichotomies, which recursively bisect the set of possible classes such that the resulting subsets can be arranged in the form of a binary tree, where each split defines a binary classification problem. Recently, a genetic algorithm for optimizing the structure of such nested dichotomies has achieved state-of-The-Art results. Motivated by its success, we propose to extend this approach using a co-evolutionary scheme to optimize both the structure of nested dichotomies and their composition into ensembles through which they are evaluated. Furthermore, we present an experimental study showing this approach to yield ensembles of nested dichotomies at substantially lower cost and, in some cases, even with an improved generalization performance.
KW - coevolution
KW - nested dichotomy
KW - supervised learning
UR - http://www.scopus.com/inward/record.url?scp=85167681437&partnerID=8YFLogxK
U2 - 10.1145/3583131.3590457
DO - 10.1145/3583131.3590457
M3 - Conference contribution
T3 - Proceedings of the Genetic and Evolutionary Computation Conference
SP - 597
EP - 605
BT - GECCO 2023 - Proceedings of the 2023 Genetic and Evolutionary Computation Conference
ER -