# Generalized Label Enhancement with Sample Correlations

arXiv: https://arxiv.org/abs/2004.03104 · HTML: https://mlsanity.com/paper/2004.03104/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Apr 2020.

## Built on by (most cited first, 9 of 9)

- [Label Distribution Learning via Implicit Distribution Representation](https://mlsanity.com/paper/2209.13824/) (2022)
- [Label Information Bottleneck for Label Enhancement](https://mlsanity.com/paper/2303.06836/) (2023)
- [Label Distribution Learning from Logical Label](https://mlsanity.com/paper/2303.06847/) (2023)
- [Label distribution learning via label correlation grid](https://mlsanity.com/paper/2210.08184/) (2022)
- [Improving Multi-Label Contrastive Learning by Leveraging Label Distribution](https://mlsanity.com/paper/2501.19145/) (2025)
- [Data Augmentation For Label Enhancement](https://mlsanity.com/paper/2303.11698/) (2023)
- [Graph based Label Enhancement for Multi-instance Multi-label learning](https://mlsanity.com/paper/2304.10705/) (2023)
- [Contrastive Label Enhancement](https://mlsanity.com/paper/2305.09500/) (2023)
- [Learning from Hard Labels with Additional Supervision on Non-Hard-Labeled Classes](https://mlsanity.com/paper/2507.18098/) (2025)

## Abstract (arXiv)

Recently, label distribution learning (LDL) has drawn much attention in machine learning, where LDL model is learned from labelel instances. Different from single-label and multi-label annotations, label distributions describe the instance by multiple labels with different intensities and accommodate to more general scenes. Since most existing machine learning datasets merely provide logical labels, label distributions are unavailable in many real-world applications. To handle this problem, we propose two novel label enhancement methods, i.e., Label Enhancement with Sample Correlations (LESC) and generalized Label Enhancement with Sample Correlations (gLESC). More specifically, LESC employs a low-rank representation of samples in the feature space, and gLESC leverages a tensor multi-rank minimization to further investigate the sample correlations in both the feature space and label space. Benefitting from the sample correlations, the proposed methods can boost the performance of label enhancement. Extensive experiments on 14 benchmark datasets demonstrate the effectiveness and superiority of our methods.