On the effectiveness of heuristics for learning nested dichotomies: an empirical analysis

V. Melnikov, E. Hüllermeier, Machine Learning (2018).

Download
Restricted OnTheEffectivenessOfHeuristics.pdf 1.48 MB
Journal Article | English
Author
;
Abstract
In machine learning, so-called nested dichotomies are utilized as a reduction technique, i.e., to decompose a multi-class classification problem into a set of binary problems, which are solved using a simple binary classifier as a base learner. The performance of the (multi-class) classifier thus produced strongly depends on the structure of the decomposition. In this paper, we conduct an empirical study, in which we compare existing heuristics for selecting a suitable structure in the form of a nested dichotomy. Moreover, we propose two additional heuristics as natural completions. One of them is the Best-of-K heuristic, which picks the (presumably) best among K randomly generated nested dichotomies. Surprisingly, and in spite of its simplicity, it turns out to outperform the state of the art.
Publishing Year
Journal Title
Machine Learning
ISSN
LibreCat-ID

Cite this

Melnikov V, Hüllermeier E. On the effectiveness of heuristics for learning nested dichotomies: an empirical analysis. Machine Learning. 2018. doi:10.1007/s10994-018-5733-1
Melnikov, V., & Hüllermeier, E. (2018). On the effectiveness of heuristics for learning nested dichotomies: an empirical analysis. Machine Learning. https://doi.org/10.1007/s10994-018-5733-1
@article{Melnikov_Hüllermeier_2018, title={On the effectiveness of heuristics for learning nested dichotomies: an empirical analysis}, DOI={10.1007/s10994-018-5733-1}, journal={Machine Learning}, author={Melnikov, Vitalik and Hüllermeier, Eyke}, year={2018} }
Melnikov, Vitalik, and Eyke Hüllermeier. “On the Effectiveness of Heuristics for Learning Nested Dichotomies: An Empirical Analysis.” Machine Learning, 2018. https://doi.org/10.1007/s10994-018-5733-1.
V. Melnikov and E. Hüllermeier, “On the effectiveness of heuristics for learning nested dichotomies: an empirical analysis,” Machine Learning, 2018.
Melnikov, Vitalik, and Eyke Hüllermeier. “On the Effectiveness of Heuristics for Learning Nested Dichotomies: An Empirical Analysis.” Machine Learning, 2018, doi:10.1007/s10994-018-5733-1.
Main File(s)
File Name
OnTheEffectivenessOfHeuristics.pdf 1.48 MB
Access Level
Restricted Closed Access
Last Uploaded
2018-11-02T15:30:57Z


Export

Marked Publications

Open Data LibreCat

Search this title in

Google Scholar