# Scalable Label Distribution Learning for Multi-Label Classification

arXiv: https://arxiv.org/abs/2311.16556 · HTML: https://mlsanity.com/paper/2311.16556/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 91 references that are in the map.
- First posted on arXiv 28 Nov 2023.

## Builds on (most cited first, 21 of 21)

- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Asymmetric Loss For Multi-Label Classification](https://mlsanity.com/paper/2009.14119/) (2020)
- [Label Distribution Learning](https://mlsanity.com/paper/1408.6027/) (2014)
- [Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets](https://mlsanity.com/paper/2007.09654/) (2020)
- [Deep Label Distribution Learning with Label Ambiguity](https://mlsanity.com/paper/1611.01731/) (2016)
- [AttentionXML: Label Tree-based Attention-Aware Deep Model for High-Performance Extreme Multi-Label Text Classification](https://mlsanity.com/paper/1811.01727/) (2018)
- [The Emerging Trends of Multi-Label Learning](https://mlsanity.com/paper/2011.11197/) (2020)
- [SGM: Sequence Generation Model for Multi-label Classification](https://mlsanity.com/paper/1806.04822/) (2018)
- [Document-level Relation Extraction as Semantic Segmentation](https://mlsanity.com/paper/2106.03618/) (2021)
- [DiSMEC - Distributed Sparse Machines for Extreme Multi-label Classification](https://mlsanity.com/paper/1609.02521/) (2016)
- [Bonsai -- Diverse and Shallow Trees for Extreme Multi-label Classification](https://mlsanity.com/paper/1904.08249/) (2019)
- [Balancing Methods for Multi-label Text Classification with Long-Tailed Class Distribution](https://mlsanity.com/paper/2109.04712/) (2021)
- [Label Distribution Learning Forests](https://mlsanity.com/paper/1702.06086/) (2017)
- [Deep Extreme Multi-label Learning](https://mlsanity.com/paper/1704.03718/) (2017)
- [One Positive Label is Sufficient: Single-Positive Multi-Label Learning with Label Enhancement](https://mlsanity.com/paper/2206.00517/) (2022)
- [Label Distributionally Robust Losses for Multi-class Classification: Consistency, Robustness and Adaptivity](https://mlsanity.com/paper/2112.14869/) (2021)
- [MuMIC -- Multimodal Embedding for Multi-label Image Classification with Tempered Sigmoid](https://mlsanity.com/paper/2211.05232/) (2022)
- [Cost-Sensitive Label Embedding for Multi-Label Classification](https://mlsanity.com/paper/1603.09048/) (2016)
- [Ranking-Based Autoencoder for Extreme Multi-label Classification](https://mlsanity.com/paper/1904.05937/) (2019)
- [Multi-Label Learning with Label Enhancement](https://mlsanity.com/paper/1706.08323/) (2017)
- [Unsupervised Feature Learning Architecture with Multi-clustering Integration RBM](https://mlsanity.com/paper/1812.01967/) (2018)

## Abstract (arXiv)

Multi-label classification (MLC) refers to the problem of tagging a given instance with a set of relevant labels. Most existing MLC methods are based on the assumption that the correlation of two labels in each label pair is symmetric, which is violated in many real-world scenarios. Moreover, most existing methods design learning processes associated with the number of labels, which makes their computational complexity a bottleneck when scaling up to large-scale output space. To tackle these issues, we propose a novel method named Scalable Label Distribution Learning (SLDL) for multi-label classification which can describe different labels as distributions in a latent space, where the label correlation is asymmetric and the dimension is independent of the number of labels. Specifically, SLDL first converts labels into continuous distributions within a low-dimensional latent space and leverages the asymmetric metric to establish the correlation between different labels. Then, it learns the mapping from the feature space to the latent space, resulting in the computational complexity is no longer related to the number of labels. Finally, SLDL leverages a nearest-neighbor-based strategy to decode the latent representations and obtain the final predictions. Extensive experiments illustrate that SLDL achieves very competitive classification performances with little computational consumption.