# Label Distribution Learning from Logical Label

arXiv: https://arxiv.org/abs/2303.06847 · HTML: https://mlsanity.com/paper/2303.06847/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 33 references that are in the map.
- First posted on arXiv 13 Mar 2023.

## Builds on (most cited first, 8 of 8)

- [Label Distribution Learning](https://mlsanity.com/paper/1408.6027/) (2014)
- [SCUT-FBP5500: A Diverse Benchmark Dataset for Multi-Paradigm Facial Beauty Prediction](https://mlsanity.com/paper/1801.06345/) (2018)
- [Label Distribution Learning Forests](https://mlsanity.com/paper/1702.06086/) (2017)
- [SCUT-FBP: A Benchmark Dataset for Facial Beauty Perception](https://mlsanity.com/paper/1511.02459/) (2015)
- [Generalized Label Enhancement with Sample Correlations](https://mlsanity.com/paper/2004.03104/) (2020)
- [Multi-Label Learning with Label Enhancement](https://mlsanity.com/paper/1706.08323/) (2017)
- [Clustering-aware Graph Construction: A Joint Learning Perspective](https://mlsanity.com/paper/1905.01446/) (2019)
- [Bidirectional Loss Function for Label Enhancement and Distribution Learning](https://mlsanity.com/paper/2007.03181/) (2020)

## Built on by (most cited first, 3 of 3)

- [Improving Multi-Label Contrastive Learning by Leveraging Label Distribution](https://mlsanity.com/paper/2501.19145/) (2025)
- [Concentration Distribution Learning from Label Distributions](https://mlsanity.com/paper/2505.21576/) (2025)
- [Towards Better IncomLDL: We Are Unaware of Hidden Labels in Advance](https://mlsanity.com/paper/2511.12494/) (2025)

## Abstract (arXiv)

Label distribution learning (LDL) is an effective method to predict the label description degree (a.k.a. label distribution) of a sample. However, annotating label distribution (LD) for training samples is extremely costly. So recent studies often first use label enhancement (LE) to generate the estimated label distribution from the logical label and then apply external LDL algorithms on the recovered label distribution to predict the label distribution for unseen samples. But this step-wise manner overlooks the possible connections between LE and LDL. Moreover, the existing LE approaches may assign some description degrees to invalid labels. To solve the above problems, we propose a novel method to learn an LDL model directly from the logical label, which unifies LE and LDL into a joint model, and avoids the drawbacks of the previous LE methods. Extensive experiments on various datasets prove that the proposed approach can construct a reliable LDL model directly from the logical label, and produce more accurate label distribution than the state-of-the-art LE methods.