# Label Distribution Learning with Biased Annotations by Learning Multi-Label Representation

arXiv: https://arxiv.org/abs/2502.01170 · HTML: https://mlsanity.com/paper/2502.01170/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 23 references that are in the map.
- First posted on arXiv 3 Feb 2025.

## Builds on (most cited first, 5 of 5)

- [Label Distribution Learning](https://mlsanity.com/paper/1408.6027/) (2014)
- [Multi-Label Learning with Global and Local Label Correlation](https://mlsanity.com/paper/1704.01415/) (2017)
- [Exploiting Multi-Label Correlation in Label Distribution Learning](https://mlsanity.com/paper/2308.01742/) (2023)
- [Inaccurate Label Distribution Learning](https://mlsanity.com/paper/2302.13000/) (2023)
- [Inaccurate Label Distribution Learning with Dependency Noise](https://mlsanity.com/paper/2405.16474/) (2024)

## Built on by (most cited first, 5 of 5)

- [Global Prompt Refinement with Non-Interfering Attention Masking for One-Shot Federated Learning](https://mlsanity.com/paper/2509.22700/) (2025)
- [Detecting Unobserved Confounders: A Kernelized Regression Approach](https://mlsanity.com/paper/2601.00200/) (2026)
- [Geometrically Regularized Transfer Learning with On-Manifold and Off-Manifold Perturbation](https://mlsanity.com/paper/2505.15191/) (2025)
- [Disentangled Geometric Alignment with Adaptive Contrastive Perturbation for Reliable Domain Transfer](https://mlsanity.com/paper/2505.15241/) (2025)
- [Dynamic Epsilon Scheduling: A Multi-Factor Adaptive Perturbation Budget for Adversarial Training](https://mlsanity.com/paper/2506.04263/) (2025)

## Abstract (arXiv)

Multi-label learning (MLL) has gained attention for its ability to represent real-world data. Label Distribution Learning (LDL), an extension of MLL to learning from label distributions, faces challenges in collecting accurate label distributions. To address the issue of biased annotations, based on the low-rank assumption, existing works recover true distributions from biased observations by exploring the label correlations. However, recent evidence shows that the label distribution tends to be full-rank, and naive apply of low-rank approximation on biased observation leads to inaccurate recovery and performance degradation. In this paper, we address the LDL with biased annotations problem from a novel perspective, where we first degenerate the soft label distribution into a hard multi-hot label and then recover the true label information for each instance. This idea stems from an insight that assigning hard multi-hot labels is often easier than assigning a soft label distribution, and it shows stronger immunity to noise disturbances, leading to smaller label bias. Moreover, assuming that the multi-label space for predicting label distributions is low-rank offers a more reasonable approach to capturing label correlations. Theoretical analysis and experiments confirm the effectiveness and robustness of our method on real-world datasets.