Progressive Identification of True Labels for Partial-Label Learning
arXiv:2002.08053
Abstract
Partial-label learning (PLL) is a typical weakly supervised learning problem, where each training instance is equipped with a set of candidate labels among which only one is the true label. Most existing methods elaborately designed learning objectives as constrained optimizations that must be solved in specific manners, making their computational complexity a bottleneck for scaling up to big data. The goal of this paper is to propose a novel framework of PLL with flexibility on the model and optimization algorithm. More specifically, we propose a novel estimator of the classification risk, theoretically analyze the classifier-consistency, and establish an estimation error bound. Then we propose a progressive identification algorithm for approximately minimizing the proposed risk estimator, where the update of the model and identification of true labels are conducted in a seamless manner. The resulting algorithm is model-independent and loss-independent, and compatible with stochastic optimization. Thorough experiments demonstrate it sets the new state of the art.
arXiv commentIn Proceedings of the 37th International Conference on Machine Learning (ICML 2020)
References in corpus (9)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- A Closer Look at Memorization in Deep Networks
- Are Anchor Points Really Indispensable in Label-Noise Learning?
- Learning from Complementary Labels
- On the Minimal Supervision for Training Any Binary Classifier from Only Unlabeled Data
- Semi-Supervised Learning via Compact Latent Space Clustering
- Network Cooperation with Progressive Disambiguation for Partial Label Learning