Cranking: Combining Rankings Using Conditional Probability Models on Permutations
Abstract
A new approach to ensemble learning is introduced that takes ranking rather than classification as fundamental, leading to models on the symmetric group and its cosets. The approach uses a generalization of the Mallows model on permutations to combine multiple input rankings. Applications include the task of combining the output of multiple search engines and multiclass or multilabel classification, where a set of input classifiers is viewed as generating a ranking of class labels. Experiments for both types of applications are presented. 1.
Cite
Text
Lebanon and Lafferty. "Cranking: Combining Rankings Using Conditional Probability Models on Permutations." International Conference on Machine Learning, 2002.Markdown
[Lebanon and Lafferty. "Cranking: Combining Rankings Using Conditional Probability Models on Permutations." International Conference on Machine Learning, 2002.](https://mlanthology.org/icml/2002/lebanon2002icml-cranking/)BibTeX
@inproceedings{lebanon2002icml-cranking,
title = {{Cranking: Combining Rankings Using Conditional Probability Models on Permutations}},
author = {Lebanon, Guy and Lafferty, John D.},
booktitle = {International Conference on Machine Learning},
year = {2002},
pages = {363-370},
url = {https://mlanthology.org/icml/2002/lebanon2002icml-cranking/}
}