# Diffusion Disambiguation Models for Partial Label Learning

arXiv: https://arxiv.org/abs/2507.00411 · HTML: https://mlsanity.com/paper/2507.00411/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 21 of its 68 references that are in the map.
- First posted on arXiv 1 Jul 2025.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 21 of 21)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Deep Learning for Classical Japanese Literature](https://mlsanity.com/paper/1812.01718/) (2018)
- [Using Pre-Training Can Improve Model Robustness and Uncertainty](https://mlsanity.com/paper/1901.09960/) (2019)
- [DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents](https://mlsanity.com/paper/2201.00308/) (2022)
- [CARD: Classification and Regression Diffusion Models](https://mlsanity.com/paper/2206.07275/) (2022)
- [Progressive Identification of True Labels for Partial-Label Learning](https://mlsanity.com/paper/2002.08053/) (2020)
- [Leveraged Weighted Loss for Partial Label Learning](https://mlsanity.com/paper/2106.05731/) (2021)
- [Dif-Fusion: Towards High Color Fidelity in Infrared and Visible Image Fusion with Diffusion Models](https://mlsanity.com/paper/2301.08072/) (2023)
- [Instance-Dependent Partial Label Learning](https://mlsanity.com/paper/2110.12911/) (2021)
- [Deep Learning from Noisy Image Labels with Quality Embedding](https://mlsanity.com/paper/1711.00583/) (2017)
- [MVP-Shot: Multi-Velocity Progressive-Alignment Framework for Few-Shot Action Recognition](https://mlsanity.com/paper/2405.02077/) (2024)
- [PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learning](https://mlsanity.com/paper/2201.08984/) (2022)
- [Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels](https://mlsanity.com/paper/2305.19518/) (2023)
- [Network Cooperation with Progressive Disambiguation for Partial Label Learning](https://mlsanity.com/paper/2002.11919/) (2020)
- [CroSel: Cross Selection of Confident Pseudo Labels for Partial-Label Learning](https://mlsanity.com/paper/2303.10365/) (2023)

## Abstract (arXiv)

Learning from ambiguous labels is a long-standing problem in practical machine learning applications. The purpose of partial label learning (PLL) is to identify the ground-truth label from a set of candidate labels associated with a given instance. Inspired by the remarkable performance of diffusion models in various generation tasks, this paper explores their potential to denoise ambiguous labels through the reverse denoising process. Therefore, this paper reformulates the label disambiguation problem from the perspective of generative models, where labels are generated by iteratively refining initial random guesses. This perspective enables the diffusion model to learn how label information is generated stochastically. By modeling the generation uncertainty, we can use the maximum likelihood estimate of the label for classification inference. However, such ambiguous labels lead to a mismatch between instance and label, which reduces the quality of generated data. To address this issue, this paper proposes a diffusion disambiguation model for PLL (DDMP), which first uses the potential complementary information between instances and labels to construct pseudo-clean labels for initial diffusion training. Furthermore, a transition-aware matrix is introduced to estimate the potential ground-truth labels, which are dynamically updated during the diffusion generation. During training, the ground-truth label is progressively refined, improving the classifier. Experiments show the advantage of the DDMP and its suitability for PLL.