beta-risk: a New Surrogate Risk for Learning from Weakly Labeled Data

Valentina Zantedeschi (1) , Rémi Emonet (1) , Marc Sebban (1)

1 LHC - Laboratoire Hubert Curien

During the past few years, the machine learning community has paid attention to developing new methods for learning from weakly labeled data. This field covers different settings like semi-supervised learning, learning with label proportions, multi-instance learning, noise-tolerant learning, etc. This paper presents a generic framework to deal with these weakly labeled scenarios. We introduce the \betarisk as a generalized formulation of the standard empirical risk based on surrogate margin-based loss functions. This risk allows us to express the reliability on the labels and to derive different kinds of learning algorithms. We specifically focus on SVMs and propose a soft margin \betasvm algorithm which behaves better that the state of the art.

Domaines: Apprentissage [cs.LG]

Valentina Zantedeschi, Rémi Emonet, Marc Sebban. beta-risk: a New Surrogate Risk for Learning from Weakly Labeled Data. NIPS 2016, Dec 2016, Barcelona, Spain. ⟨hal-01359298⟩