Cranking: Combining Rankings Using Conditional Probability Models on Permutations

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.

• Type: Conference
• Year: 2002
• Where: ICML
• Authors: Guy Lebanon, John D. Lafferty
• Keywords: ICML 2002, Input Classifiers, Machine Learning, Multiple Input Rankings, Multiple Search Engines