# Label Distribution Learning

arXiv: https://arxiv.org/abs/1408.6027 · HTML: https://mlsanity.com/paper/1408.6027/

## Key facts

- Cited by 124 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Aug 2014.

## Built on by (most cited first, 30 of 124)

- [Distilling Virtual Examples for Long-tailed Recognition](https://mlsanity.com/paper/2103.15042/) (2021)
- [To Smooth or Not? When Label Smoothing Meets Noisy Labels](https://mlsanity.com/paper/2106.04149/) (2021)
- [Instance-Dependent Partial Label Learning](https://mlsanity.com/paper/2110.12911/) (2021)
- [PML: Progressive Margin Loss for Long-tailed Age Classification](https://mlsanity.com/paper/2103.02140/) (2021)
- [Uncertainty-aware Label Distribution Learning for Facial Expression Recognition](https://mlsanity.com/paper/2209.10448/) (2022)
- [Unimodal-Concentrated Loss: Fully Adaptive Label Distribution Learning for Ordinal Regression](https://mlsanity.com/paper/2204.00309/) (2022)
- [Advancing Social Intelligence in AI Agents: Technical Challenges and Open Questions](https://mlsanity.com/paper/2404.11023/) (2024)
- [FP-Age: Leveraging Face Parsing Attention for Facial Age Estimation in the Wild](https://mlsanity.com/paper/2106.11145/) (2021)
- [Exploiting Multi-Label Correlation in Label Distribution Learning](https://mlsanity.com/paper/2308.01742/) (2023)
- [Auto-Encoding Score Distribution Regression for Action Quality Assessment](https://mlsanity.com/paper/2111.11029/) (2021)
- [A Circular-Structured Representation for Visual Emotion Distribution Learning](https://mlsanity.com/paper/2106.12450/) (2021)
- [Improving Face-Based Age Estimation with Attention-Based Dynamic Patch Fusion](https://mlsanity.com/paper/2112.10167/) (2021)
- [Modeling Multimodal Aleatoric Uncertainty in Segmentation with Mixture of Stochastic Experts](https://mlsanity.com/paper/2212.07328/) (2022)
- [Inaccurate Label Distribution Learning](https://mlsanity.com/paper/2302.13000/) (2023)
- [Transfer and Share: Semi-Supervised Learning from Long-Tailed Data](https://mlsanity.com/paper/2205.13358/) (2022)
- [Graph Decoupling Attention Markov Networks for Semi-supervised Graph Node Classification](https://mlsanity.com/paper/2104.13718/) (2021)
- [Learning From Biased Soft Labels](https://mlsanity.com/paper/2302.08155/) (2023)
- [ULTRA: Uncertainty-aware Label Distribution Learning for Breast Tumor Cellularity Assessment](https://mlsanity.com/paper/2206.06623/) (2022)
- [A Survey on Extreme Multi-label Learning](https://mlsanity.com/paper/2210.03968/) (2022)
- [Subjective Crowd Disagreements for Subjective Data: Uncovering Meaningful CrowdOpinion with Population-level Learning](https://mlsanity.com/paper/2307.10189/) (2023)
- [Label Distribution Learning via Implicit Distribution Representation](https://mlsanity.com/paper/2209.13824/) (2022)
- [Learning with Confidence: Training Better Classifiers from Soft Labels](https://mlsanity.com/paper/2409.16071/) (2024)
- [Label Distribution Learning for Generalizable Multi-source Person Re-identification](https://mlsanity.com/paper/2204.05903/) (2022)
- [Seeking Subjectivity in Visual Emotion Distribution Learning](https://mlsanity.com/paper/2207.11875/) (2022)
- [Do We Fully Understand Students' Knowledge States? Identifying and Mitigating Answer Bias in Knowledge Tracing](https://mlsanity.com/paper/2308.07779/) (2023)
- [Manipulating the Label Space for In-Context Classification](https://mlsanity.com/paper/2312.00351/) (2023)
- [Label Distribution Learning with Biased Annotations by Learning Multi-Label Representation](https://mlsanity.com/paper/2502.01170/) (2025)
- [Wallpaper Texture Generation and Style Transfer Based on Multi-label Semantics](https://mlsanity.com/paper/2106.11482/) (2021)
- [Many Ways to Be Lonely: Fine-Grained Characterization of Loneliness and Its Potential Changes in COVID-19](https://mlsanity.com/paper/2201.07423/) (2022)
- [Adaptive Mean-Residue Loss for Robust Facial Age Estimation](https://mlsanity.com/paper/2203.17156/) (2022)

## Abstract (arXiv)

Although multi-label learning can deal with many problems with label ambiguity, it does not fit some real applications well where the overall distribution of the importance of the labels matters. This paper proposes a novel learning paradigm named label distribution learning (LDL) for such kind of applications. The label distribution covers a certain number of labels, representing the degree to which each label describes the instance. LDL is a more general learning framework which includes both single-label and multi-label learning as its special cases. This paper proposes six working LDL algorithms in three ways: problem transformation, algorithm adaptation, and specialized algorithm design. In order to compare the performance of the LDL algorithms, six representative and diverse evaluation measures are selected via a clustering analysis, and the first batch of label distribution datasets are collected and made publicly available. Experimental results on one artificial and fifteen real-world datasets show clear advantages of the specialized algorithms, which indicates the importance of special design for the characteristics of the LDL problem.