A general framework for adversarial label learning

MaRDI QIDQ4999093zbMATH OpenFDO

Authors Chidubem Arachie, Bert Huang

Publication date 9 July 2021

Full work available at URL https://jmlr.csail.mit.edu/papers/v22/20-537.html

zbMATH Keywords

unsupervised learningconstraint learningadversarial learningLagrangian optimizationweak supervision

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Learning safe multi-label prediction for weakly labeled data
• Learning With Proper Partial Labels
• Convex and scalable weakly labeled SVMs
• Learning multi labels from single label -- an extreme weak label learning algorithm
• A theory of learning with corrupted labels

Cites work

• Adaptive subgradient methods for online learning and stochastic optimization
• Generalized expectation criteria for semi-supervised learning with weakly labeled data
• Multiplier and gradient methods
• Posterior regularization for structured latent variable models

Cited in

(5)

• Learning from fuzzy labels: theoretical issues and algorithmic solutions
• Structural, Syntactic, and Statistical Pattern Recognition
• Tackling biased complementary label learning with large margin
• Learning adaptive classifiers synthesis for generalized few-shot learning
• Adversarial supervised contrastive learning

Describes a project that uses

Uses Software

• Flickr30K
• Fashion-MNIST
• UCI

This page was built for publication: A general framework for adversarial label learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4999093)