Multi-Level Generative Models for Partial Label Learning with Non-random Label Noise
This work addresses the problem of learning from noisy candidate labels for machine learning practitioners, representing an incremental improvement with a novel hybrid method.
The paper tackles partial label learning with non-random label noise by proposing a multi-level generative model (MGPLL) that learns adversarial generators for label denoising and feature mapping, achieving state-of-the-art performance in experiments on synthetic and real-world datasets.
Partial label (PL) learning tackles the problem where each training instance is associated with a set of candidate labels that include both the true label and irrelevant noise labels. In this paper, we propose a novel multi-level generative model for partial label learning (MGPLL), which tackles the problem by learning both a label level adversarial generator and a feature level adversarial generator under a bi-directional mapping framework between the label vectors and the data samples. Specifically, MGPLL uses a conditional noise label generation network to model the non-random noise labels and perform label denoising, and uses a multi-class predictor to map the training instances to the denoised label vectors, while a conditional data feature generator is used to form an inverse mapping from the denoised label vectors to data samples. Both the noise label generator and the data feature generator are learned in an adversarial manner to match the observed candidate labels and data features respectively. Extensive experiments are conducted on synthesized and real-world partial label datasets. The proposed approach demonstrates the state-of-the-art performance for partial label learning.