DFG Project Pairwise Learning
The project proposal Learning by Pairwise Comparison for Problems with Structured Output Spaces has been accepted by the German Research Foundation (DFG).
In this project, which we jointly proposed with Prof. Eyke Hüllermeier (Philipps-Universität Marburg), we will continue our research on pairwise classification. The goal of the project is a general and coherent unifying framework in which problems with structured output spaces, such as multi-label, hierarichical or ordered classification, can be solved by pairwise methods in a principled manner.
The project will start in May 2007 for a duration of 24 months.