$\propto$SVM for learning with label proportions

Abstract

We study the problem of learning with label proportions in which the training data is provided in groups and only the proportion of each class in each group is known. We propose a new method called proportion-SVM, or $\propto$SVM, which explicitly models the latent unknown instance labels together with the known group label proportions in a large-margin framework. Unlike the existing works, our approach avoids making restrictive assumptions about the data. The $\propto$SVM model leads to a non-convex integer programming problem. In order to solve it efficiently, we propose two algorithms: one based on simple alternating optimization and the other based on a convex relaxation. Extensive experiments on standard datasets show that $\propto$SVM outperforms the state-of-the-art, especially for larger group sizes.

Appears in Proceedings of the 30th International Conference on Machine Learning (ICML 2013)

References in corpus (1)

• Alternating Projections for Learning with Expectation Constraints

Cited by in corpus (7)

• Lung and Pancreatic Tumor Characterization in the Deep Learning Era: Novel Supervised and Unsupervised Learning Approaches
• Video Representation Learning Using Discriminative Pooling
• Stochastic EM for Shuffled Linear Regression
• Learning from Label Proportions with Consistency Regularization
• Label Propagation for Learning with Label Proportions
• Discriminative Video Representation Learning Using Support Vector Classifiers
• Transfer Learning-Based Label Proportions Method with Data of Uncertainty