Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Learning from Label Proportions: A Mutual Contamination Framework

About

Learning from label proportions (LLP) is a weakly supervised setting for classification in which unlabeled training instances are grouped into bags, and each bag is annotated with the proportion of each class occurring in that bag. Prior work on LLP has yet to establish a consistent learning procedure, nor does there exist a theoretically justified, general purpose training criterion. In this work we address these two issues by posing LLP in terms of mutual contamination models (MCMs), which have recently been applied successfully to study various other weak supervision settings. In the process, we establish several novel technical results for MCMs, including unbiased losses and generalization error bounds under non-iid sampling plans. We also point out the limitations of a common experimental setting for LLP, and propose a new one based on our MCM framework.

Clayton Scott, Jianxin Zhang• 2020

Related benchmarks

TaskDatasetResultRank
ClassificationAdult
ROCAUC0.8644
32
Binary Classificationadult (AD) (test)
AUROC0.8728
32
Binary ClassificationMAGIC [0, 1/2]
AUC0.8909
20
Binary Classificationmagic
AUC0.8911
20
Showing 4 of 4 rows

Other info

Follow for update