# Multi-Level Generative Models for Partial Label Learning with Non-random Label Noise

arXiv: https://arxiv.org/abs/2005.05407 · HTML: https://mlsanity.com/paper/2005.05407/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 May 2020.

## Built on by (most cited first, 4 of 4)

- [SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning](https://mlsanity.com/paper/2209.10365/) (2022)
- [Learning with Partial Labels from Semi-supervised Perspective](https://mlsanity.com/paper/2211.13655/) (2022)
- [Robust Representation Learning for Unreliable Partial Label Learning](https://mlsanity.com/paper/2308.16718/) (2023)
- [Towards Robust Incremental Learning under Ambiguous Supervision](https://mlsanity.com/paper/2501.13584/) (2025)

## Abstract (arXiv)

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.