Adaptive Large Margin Training for Multilabel Classification

Authors

  • Yuhong Guo Temple University
  • Dale Schuurmans University of Alberta

Abstract

Multilabel classification is a central problem in many areas of data analysis, including text and multimedia categorization, where individual data objects need to be assigned multiple labels. A key challenge in these tasks is to learn a classifier that can properly exploit label correlations without requiring exponential enumeration of label subsets during training or testing. We investigate novel loss functions for multilabel training within a large margin framework---identifying a simple alternative that yields improved generalization while still allowing efficient training. We furthermore show how covariances between the label models can be learned simultaneously with the classification model itself, in a jointly convex formulation, without compromising scalability. The resulting combination yields state of the art accuracy in multilabel webpage classification.

Downloads

Published

2011-08-04

How to Cite

Guo, Y., & Schuurmans, D. (2011). Adaptive Large Margin Training for Multilabel Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 25(1), 374-379. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/7895

Issue

Section

AAAI Technical Track: Machine Learning