Learning structured models with the AUC loss and its generalizations

Nir Rosenfeld, Ofer Meshi, Danny Tarlow, Amir Globerson

Research output: Contribution to journalConference articlepeer-review

Abstract

Many problems involve the prediction of multiple, possibly dependent labels. The structured output prediction framework builds predictors that take these dependencies into account and use them to improve accuracy. In many such tasks, performance is evaluated by the Area Under the ROC Curve (AUC). While a framework for optimizing the AUC loss for unstructured models exists, it does not naturally extend to structured models. In this work, we propose a representation and learning formulation for optimizing structured models over the AUC loss, show how our approach generalizes the unstructured case, and provide algorithms for solving the resulting inference and learning problems. We also explore several new variants of the AUC measure which naturally arise from our formulation. Finally, we empirically show the utility of our approach in several domains.

Original languageEnglish
Pages (from-to)841-849
Number of pages9
JournalJournal of Machine Learning Research
Volume33
StatePublished - 2014
Externally publishedYes
Event17th International Conference on Artificial Intelligence and Statistics, AISTATS 2014 - Reykjavik, Iceland
Duration: 22 Apr 201425 Apr 2014

Fingerprint

Dive into the research topics of 'Learning structured models with the AUC loss and its generalizations'. Together they form a unique fingerprint.

Cite this