Partial Label Learning with Self-Guided Retraining

2019/02/08 by Lei Feng, Bo An, Feng, Lei +1 · 8 citations
Computer Science · Mathematics · #Advanced Image and Video Retrieval Techniques #Algorithm #Artificial intelligence #Computer science #Convex function #FOS: Computer and information sciences #Leverage (statistics) #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Data Classification #Machine learning #Mathematical optimization #Mathematics #Optimization problem #Quadratic programming #Regular polygon #Regularization (linguistics) #Set (abstract data type) #Text and Document Classification Technologies #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.1902.03045

published in arXiv (Cornell University) (Cornell University) · 8 pages, accepted by AAAI-19

arxiv created 2019/02/08 · openalex publication_date 2019/02/08 · arxiv updated 2019/02/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Abstract

Partial label learning deals with the problem where each training instance is assigned a set of candidate labels, only one of which is correct. This paper provides the first attempt to leverage the idea of self-training for dealing with partially labeled examples. Specifically, we propose a unified formulation with proper constraints to train the desired model and perform pseudo-labeling jointly. For pseudo-labeling, unlike traditional self-training that manually differentiates the ground-truth label with enough high confidence, we introduce the maximum infinity norm regularization on the modeling outputs to automatically achieve this consideratum, which results in a convex-concave optimization problem. We show that optimizing this convex-concave problem is equivalent to solving a set of quadratic programming (QP) problems. By proposing an upper-bound surrogate objective function, we turn to solving only one QP problem for improving the optimization efficiency. Extensive experiments on synthesized and real-world datasets demonstrate that the proposed approach significantly outperforms the state-of-the-art partial label learning approaches.

Cited by

• Human-Corrected Labels Learning: Enhancing Labels Quality via Human Correction of VLMs Discrepancies
• Amortized Variational Inference for Partial-Label Learning: A Probabilistic Approach to Label Disambiguation
• Learning from N-Tuple Data with M Positive Instances: Unbiased Risk Estimation and Theoretical Guarantees
• Analytical Survey of Learning with Low-Resource Data: From Analysis to Investigation
• A Unified Empirical Risk Minimization Framework for Flexible N-Tuples Weak Supervision
• Partial Label Learning for Automated Theorem Proving
• Why Can Accurate Models Be Learned from Inaccurate Annotations?
• Mean Estimation from Coarse Data: Characterizations and Efficient Algorithms

Related

• A Self-paced Regularization Framework for Partial-Label Learning
• Learning with Partial Labels from Semi-supervised Perspective
• Provably Consistent Partial-Label Learning
• Learning with Proper Partial Labels
• Progressive Identification of True Labels for Partial-Label Learning