Structured Prediction with Partial Labelling through the Infimum Loss
This provides a general solution for reducing annotation costs in various learning problems, though it is incremental as it builds on existing partial labeling methods.
The paper tackles the problem of weak supervision in supervised learning by introducing a unified framework for structured prediction with partial labeling, which leads to explicit algorithms with proven statistical consistency and learning rates, and experiments show it outperforms common baselines.
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 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.