# Label Information Bottleneck for Label Enhancement

arXiv: https://arxiv.org/abs/2303.06836 · HTML: https://mlsanity.com/paper/2303.06836/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 34 references that are in the map.
- First posted on arXiv 13 Mar 2023.

## Builds on (most cited first, 9 of 9)

- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Disentangling Label Distribution for Long-tailed Visual Recognition](https://mlsanity.com/paper/2012.00321/) (2020)
- [Graph Information Bottleneck](https://mlsanity.com/paper/2010.12811/) (2020)
- [Label Distribution Learning](https://mlsanity.com/paper/1408.6027/) (2014)
- [The Emerging Trends of Multi-Label Learning](https://mlsanity.com/paper/2011.11197/) (2020)
- [Unsupervised Speech Decomposition via Triple Information Bottleneck](https://mlsanity.com/paper/2004.11284/) (2020)
- [Learning Representations for Neural Network-Based Classification Using the Information Bottleneck Principle](https://mlsanity.com/paper/1802.09766/) (2018)
- [Improving Subgraph Recognition with Variational Graph Information Bottleneck](https://mlsanity.com/paper/2112.09899/) (2021)
- [Generalized Label Enhancement with Sample Correlations](https://mlsanity.com/paper/2004.03104/) (2020)

## Built on by (most cited first, 4 of 4)

- [A Universal Knowledge Embedded Contrastive Learning Framework for Hyperspectral Image Classification](https://mlsanity.com/paper/2404.01673/) (2024)
- [Label Distribution Learning using the Squared Neural Family on the Probability Simplex](https://mlsanity.com/paper/2412.07324/) (2024)
- [Learning from Hard Labels with Additional Supervision on Non-Hard-Labeled Classes](https://mlsanity.com/paper/2507.18098/) (2025)
- [D3O: Dynamic Distribution Distillation for Ordinal Regression](https://mlsanity.com/paper/2607.23575/) (2026)

## Abstract (arXiv)

In this work, we focus on the challenging problem of Label Enhancement (LE), which aims to exactly recover label distributions from logical labels, and present a novel Label Information Bottleneck (LIB) method for LE. For the recovery process of label distributions, the label irrelevant information contained in the dataset may lead to unsatisfactory recovery performance. To address this limitation, we make efforts to excavate the essential label relevant information to improve the recovery performance. Our method formulates the LE problem as the following two joint processes: 1) learning the representation with the essential label relevant information, 2) recovering label distributions based on the learned representation. The label relevant information can be excavated based on the "bottleneck" formed by the learned representation. Significantly, both the label relevant information about the label assignments and the label relevant information about the label gaps can be explored in our method. Evaluation experiments conducted on several benchmark label distribution learning datasets verify the effectiveness and competitiveness of LIB. Our source codes are available https://github.com/qinghai-zheng/LIBLE