Learning from Label Proportions with Dual-proportion Constraints

2026-03-22

AI Summary

This work proposes LLP-DC, a novel method for learning from label proportions (LLP) under a weakly supervised setting where only the class proportions within sample bags are provided and instance-level labels are unavailable. LLP-DC is the first approach to incorporate instance-level proportion constraints into the LLP framework. It employs a dual-constraint mechanism: at the bag level, it enforces alignment between the mean of instance predictions and the given proportions; at the instance level, it generates hard pseudo-labels that satisfy global proportion constraints via a minimum-cost maximum-flow algorithm. Extensive experiments demonstrate that LLP-DC significantly outperforms existing LLP methods across multiple benchmark datasets and maintains consistent performance gains under varying bag sizes.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Learning from Label Proportions (LLP) is a weakly supervised problem in which the training data comprise bags, that is, groups of instances, each annotated only with bag-level class label proportions, and the objective is to learn a classifier that predicts instance-level labels. This setting is widely applicable when privacy constraints limit access to instance-level annotations or when fine-grained labeling is costly or impractical. In this work, we introduce a method that leverages Dual proportion Constraints (LLP-DC) during training, enforcing them at both the bag and instance levels. Specifically, the bag-level training aligns the mean prediction with the given proportion, and the instance-level training aligns hard pseudo-labels that satisfy the proportion constraint, where a minimum-cost maximum-flow algorithm is used to generate hard pseudo-labels. Extensive experimental results across various benchmark datasets empirically validate that LLP-DC consistently improves over previous LLP methods across datasets and bag sizes. The code is publicly available at https://github.com/TianhaoMa5/CV PR2026_Findings_LLP_DC.

Problem

• Learning from Label Proportions
• Weakly Supervised Learning
• Label Proportion
• Instance-level Classification
• Bag-level Annotation

Innovation

• Learning from Label Proportions
• Dual-proportion Constraints
• Weakly Supervised Learning
• Minimum-cost Maximum-flow
• Pseudo-labeling