Provably Consistent Partial-Label Learning
arXiv:2007.08929
Abstract
Partial-label learning (PLL) is a multi-class classification problem, where each training example is associated with a set of candidate labels. Even though many practical PLL methods have been proposed in the last two decades, there lacks a theoretical understanding of the consistency of those methods-none of the PLL methods hitherto possesses a generation process of candidate label sets, and then it is still unclear why such a method works on a specific dataset and when it may fail given a different dataset. In this paper, we propose the first generation model of candidate label sets, and develop two novel PLL methods that are guaranteed to be provably consistent, i.e., one is risk-consistent and the other is classifier-consistent. Our methods are advantageous, since they are compatible with any deep network or stochastic optimizer. Furthermore, thanks to the generation model, we would be able to answer the two questions above by testing if the generation model matches given candidate label sets. Experiments on benchmark and real-world datasets validate the effectiveness of the proposed generation model and two PLL methods.
arXiv commentNeurIPS 2020 camera-ready version
References in corpus (16)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
- Multi-Instance Multi-Label Learning
- Are Anchor Points Really Indispensable in Label-Noise Learning?
- Masking: A New Perspective of Noisy Supervision
- How does Disagreement Help Generalization against Label Corruption?
- Part-dependent Label Noise: Towards Instance-dependent Label Noise
- Learning from Complementary Labels
- Theoretical Comparisons of Positive-Unlabeled Learning against Positive-Negative Learning
- SIGUA: Forgetting May Make Learning with Noisy Labels More Robust
- Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions
- On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled Data
- Mitigating Overfitting in Supervised Classification from Two Unlabeled Datasets: A Consistent Risk Correction Approach
- Self-PU: Self Boosted and Calibrated Positive-Unlabeled Training
- Unbiased Risk Estimators Can Mislead: A Case Study of Learning with Complementary Labels