Maximum margin multi-label structured prediction Conference Paper

Author(s): Lampert, Christoph
Title: Maximum margin multi-label structured prediction
Affiliation IST Austria
Abstract: We study multi-label prediction for structured output sets, a problem that occurs, for example, in object detection in images, secondary structure prediction in computational biology, and graph matching with symmetries. Conventional multilabel classification techniques are typically not applicable in this situation, because they require explicit enumeration of the label set, which is infeasible in case of structured outputs. Relying on techniques originally designed for single-label structured prediction, in particular structured support vector machines, results in reduced prediction accuracy, or leads to infeasible optimization problems. In this work we derive a maximum-margin training formulation for multi-label structured prediction that remains computationally tractable while achieving high prediction accuracy. It also shares most beneficial properties with single-label maximum-margin approaches, in particular formulation as a convex optimization problem, efficient working set training, and PAC-Bayesian generalization bounds.
Keywords: Computational Biology; Optimization problems; Structured prediction; Prediction accuracy; Classification technique; Convex optimization problems; Generalization bound; Graph matchings; Maximum margin; Multi-label; Object Detection; Secondary structure prediction; Structured supports; Working set
Conference Title: NIPS: Neural Information Processing Systems
Conference Dates: December 12-14, 2011
Conference Location: Granada, Spain
ISBN: 10495258
Publisher: Neural Information Processing Systems  
Date Published: 2011-12-01
Start Page: 9p
Open access: no
IST Austria Authors
  1. Christoph Lampert
    87 Lampert
Related IST Austria Work