Multi-class classifiers and their underlying shared structure

Authors:
Volkan Vural;Glenn Fung;Romer Rosales;Jennifer G. Dy
Affiliations:
Department of Electrical and Computer Engineering, Northeastern University, Boston, MA;Computer Aided Diagnosis and Therapy, Siemens Medical Solutions, Malvern, PA;Computer Aided Diagnosis and Therapy, Siemens Medical Solutions, Malvern, PA;Department of Electrical and Computer Engineering, Northeastern University, Boston, MA
Venue:
IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
Year:
2009

Citing 9
Cited 0

Multicategory Classification by Support Vector Machines

Computational Optimization and Applications - Special issue on computational optimization—a tribute to Olvi Mangasarian, part I
Proximal support vector machine classifiers

Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining
Reducing multiclass to binary: a unifying approach for margin classifiers

The Journal of Machine Learning Research
On the algorithmic implementation of multiclass kernel-based vector machines

The Journal of Machine Learning Research
Convergence of alternating optimization

Neural, Parallel & Scientific Computations
A fast iterative algorithm for fisher discriminant using heterogeneous kernels

ICML '04 Proceedings of the twenty-first international conference on Machine learning
Large Margin Methods for Structured and Interdependent Output Variables

The Journal of Machine Learning Research
Uncovering shared structures in multiclass classification

Proceedings of the 24th international conference on Machine learning
Solving multiclass support vector machines with LaRank

Proceedings of the 24th international conference on Machine learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

Multi-class problems have a richer structure than binary classification problems. Thus, they can potentially improve their performance by exploiting the relationship among class labels. While for the purposes of providing an automated classification result this class structure does not need to be explicitly unveiled, for human level analysis or interpretation this is valuable. We develop a multi-class large margin classifier that extracts and takes advantage of class relationships. We provide a bi-convex formulation that explicitly learns a matrix that captures these class relationships and is decoupled from the feature weights. Our representation can take advantage of the class structure to compress themodel by reducing the number of classifiers employed, maintaining high accuracy even with large compression. In addition, we present an efficient formulation in terms of speed and memory.