Timezone: »

 
Poster
Structured Prediction with Partial Labelling through the Infimum Loss
Vivien Cabannnes · Alessandro Rudi · Francis Bach

Tue Jul 14 10:00 AM -- 10:45 AM & Tue Jul 14 11:00 PM -- 11:45 PM (PDT) @
in Poster Session 4 »

Annotating datasets is one of the main costs in nowadays supervised learning. The goal of weak supervision is to enable models to learn using only forms of labelling which are cheaper to collect, as partial labelling. This is a type of incomplete annotation where, for each datapoint, supervision is cast as a set of labels containing the real one. The problem of supervised learning with partial labelling has been studied for specific instances such as classification, multi-label, ranking or segmentation, but a general framework is still missing. This paper provides a unified framework based on structured prediction and on the concept of {\em infimum loss} to deal with partial labelling over a wide family of learning problems and loss functions. The framework leads naturally to explicit algorithms that can be easily implemented and for which proved statistical consistency and learning rates. Experiments confirm the superiority of the proposed approach over commonly used baselines.

Keywords: Kernel Methods · Structured Prediction · Unsupervised and Semi-supervised Learning · Sequential, Network, and Time-Series Modeling

Author Information

Vivien Cabannnes (INRIA)
Alessandro Rudi (École Normale Supérieure )
Francis Bach (INRIA - Ecole Normale Supérieure)

More from the Same Authors