Material Detail

This video was recorded at 26th International Conference on Machine Learning (ICML), Montreal 2009. In ranking with the pairwise classification approach, the loss associated to a predicted ranked list is the mean of the pairwise classifica- tion losses. This loss is inadequate for tasks such as information retrieval where we prefer ranked lists with high precision on the top of the list. We propose to optimize a larger class of loss functions for ranking, based on an ordered weighted average (OWA) (Yager, 88) of the classification losses. Convex OWA aggregation operators range from the max to the mean depending on their weights, and can be used to focus on the top ranked elements as they give more weight to the largest losses. When aggregating hinge losses, the optimization problem is similar to the SVM for interdependent output spaces. Moreover, we show that an OWA aggregation of margin-based classification losses has good generalization properties. Experiments on the Letor 3.0 benchmark dataset for information retrieval validate our approach.

Disciplines:

• Science and Technology  / Computer Science  / Programming & Programming Languages