# Order-free Learning Alleviating Exposure Bias in Multi-label Classification

arXiv: https://arxiv.org/abs/1909.03434 · HTML: https://mlsanity.com/paper/1909.03434/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Sep 2019.

## Built on by (most cited first, 12 of 12)

- [Balancing Methods for Multi-label Text Classification with Long-Tailed Class Distribution](https://mlsanity.com/paper/2109.04712/) (2021)
- [Enhancing Label Correlation Feedback in Multi-Label Text Classification via Multi-Task Learning](https://mlsanity.com/paper/2106.03103/) (2021)
- [CARAT: Contrastive Feature Reconstruction and Aggregation for Multi-Modal Multi-Label Emotion Recognition](https://mlsanity.com/paper/2312.10201/) (2023)
- [Multi-Label Classification for Implicit Discourse Relation Recognition](https://mlsanity.com/paper/2406.04461/) (2024)
- [Label Attention Network for Temporal Sets Prediction: You Were Looking at a Wrong Self-Attention](https://mlsanity.com/paper/2303.00280/) (2023)
- [Automatic tagging of knowledge points for K12 math problems](https://mlsanity.com/paper/2208.09867/) (2022)
- [Cluster-Guided Label Generation in Extreme Multi-Label Classification](https://mlsanity.com/paper/2302.09150/) (2023)
- [Accurate Use of Label Dependency in Multi-Label Text Classification Through the Lens of Causality](https://mlsanity.com/paper/2310.07588/) (2023)
- [Improving Imbalanced Text Classification with Dynamic Curriculum Learning](https://mlsanity.com/paper/2210.14724/) (2022)
- [Implicit Training of Energy Model for Structure Prediction](https://mlsanity.com/paper/2211.11649/) (2022)
- [A Debiased Nearest Neighbors Framework for Multi-Label Text Classification](https://mlsanity.com/paper/2408.03202/) (2024)
- [RAMer: Reconstruction-based Adversarial Model for Multi-party Multi-modal Multi-label Emotion Recognition](https://mlsanity.com/paper/2502.10435/) (2025)

## Abstract (arXiv)

Multi-label classification (MLC) assigns multiple labels to each sample. Prior studies show that MLC can be transformed to a sequence prediction problem with a recurrent neural network (RNN) decoder to model the label dependency. However, training a RNN decoder requires a predefined order of labels, which is not directly available in the MLC specification. Besides, RNN thus trained tends to overfit the label combinations in the training set and have difficulty generating unseen label sequences. In this paper, we propose a new framework for MLC which does not rely on a predefined label order and thus alleviates exposure bias. The experimental results on three multi-label classification benchmark datasets show that our method outperforms competitive baselines by a large margin. We also find the proposed approach has a higher probability of generating label combinations not seen during training than the baseline models. The result shows that the proposed approach has better generalization capability.