# Label Embedding Network: Learning Label Representation for Soft Training of Deep Networks

arXiv: https://arxiv.org/abs/1710.10393 · HTML: https://mlsanity.com/paper/1710.10393/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Oct 2017.

## Built on by (most cited first, 10 of 10)

- [Y-Tuning: An Efficient Tuning Paradigm for Large-Scale Pre-Trained Models via Label Representation Learning](https://mlsanity.com/paper/2202.09817/) (2022)
- [TPMIL: Trainable Prototype Enhanced Multiple Instance Learning for Whole Slide Image Classification](https://mlsanity.com/paper/2305.00696/) (2023)
- [Learning Structured Representations by Embedding Class Hierarchy with Fast Optimal Transport](https://mlsanity.com/paper/2410.03052/) (2024)
- [A Comprehensive Review on Harnessing Large Language Models to Overcome Recommender System Challenges](https://mlsanity.com/paper/2507.21117/) (2025)
- [Label Name is Mantra: Unifying Point Cloud Segmentation across Heterogeneous Datasets](https://mlsanity.com/paper/2303.10585/) (2023)
- [Improving Model Training via Self-learned Label Representations](https://mlsanity.com/paper/2209.04528/) (2022)
- [SSLCL: An Efficient Model-Agnostic Supervised Contrastive Learning Framework for Emotion Recognition in Conversations](https://mlsanity.com/paper/2310.16676/) (2023)
- [Automatic Alignment of Discourse Relations of Different Discourse Annotation Frameworks](https://mlsanity.com/paper/2403.20196/) (2024)
- [Hierarchical Multi-Label Generation with Probabilistic Level-Constraint](https://mlsanity.com/paper/2505.03775/) (2025)
- [MIRRA: Fast, High-Fidelity Molecular Generation with Chemistry-Informed Discrete Flow Matching](https://mlsanity.com/paper/2610.17244/) (2026)

## Abstract (arXiv)

We propose a method, called Label Embedding Network, which can learn label representation (label embedding) during the training process of deep networks. With the proposed method, the label embedding is adaptively and automatically learned through back propagation. The original one-hot represented loss function is converted into a new loss function with soft distributions, such that the originally unrelated labels have continuous interactions with each other during the training process. As a result, the trained model can achieve substantially higher accuracy and with faster convergence speed. Experimental results based on competitive tasks demonstrate the effectiveness of the proposed method, and the learned label embedding is reasonable and interpretable. The proposed method achieves comparable or even better results than the state-of-the-art systems. The source code is available at urlhttps://github.com/lancopku/LabelEmb.