We propose a method for jointly inferring labels across a collection of data samples, where each sample consists of an observation and a prior belief about the label. By implicitly assuming the existence of a generative model for which a differentiable predictor is the posterior, we derive a training objective that allows learning under weak beliefs. This formulation unifies various machine learning settings; the weak beliefs can come in the form of noisy or incomplete labels, likelihoods given by a different prediction mechanism on auxiliary input, or common-sense priors reflecting knowledge about the structure of the problem at hand. We demonstrate the proposed algorithms on diverse problems: classification with negative training examples, learning from rankings, weakly and self-supervised aerial imagery segmentation, co-segmentation of video frames, and coarsely supervised text classification.
@article{arxiv.2202.14000,
title = {Resolving label uncertainty with implicit posterior models},
author = {Esther Rolf and Nikolay Malkin and Alexandros Graikos and Ana Jojic and Caleb Robinson and Nebojsa Jojic},
journal= {arXiv preprint arXiv:2202.14000},
year = {2022}
}