Easy Learning from Label Proportions

Robert Istvan Busa-Fekete, Heejin Choi, Travis Dick, Claudio Gentile, Andres Munoz medina

Keywords: learning with partial information, unbiased loss, classification, proportion matching

TL;DR: We propose a simple and flexible method for learning with label proportions and investigate applications to widely used learning methods, like ERM and SGD.

Abstract: We consider the problem of Learning from Label Proportions (LLP), a weakly supervised classification setup where instances are grouped into i.i.d. “bags”, and only the frequency of class labels at each bag is available. Albeit, the objective of the learner is to achieve low task loss at an individual instance level. Here we propose EASYLLP, a flexible and simple-to-implement debiasing approach based on aggregate labels, which operates on arbitrary loss functions. Our technique allows us to accurately estimate the expected loss of an arbitrary model at an individual level. We elucidate the differences between our method and standard methods based on label proportion matching, in terms of applicability and optimality conditions. We showcase the flexibility of our approach compared to alternatives by applying our method to popular learning frameworks, like Empirical Risk Minimization (ERM) and Stochastic Gradient Descent (SGD) with provable guarantees on instance level performance. Finally, we validate our theoretical results on multiple datasets, empirically illustrating the conditions under which our algorithm is expected to perform better or worse than previous LLP approaches

Submission Number: 9026