# Batch Selection for Multi-Label Classification Guided by Uncertainty and Dynamic Label Correlations

arXiv: https://arxiv.org/abs/2412.16521 · HTML: https://mlsanity.com/paper/2412.16521/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 30 references that are in the map.
- First posted on arXiv 21 Dec 2024.

## Builds on (most cited first, 13 of 13)

- [Training Region-based Object Detectors with Online Hard Example Mining](https://mlsanity.com/paper/1604.03540/) (2016)
- [Not All Samples Are Created Equal: Deep Learning with Importance Sampling](https://mlsanity.com/paper/1803.00942/) (2018)
- [Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samples](https://mlsanity.com/paper/1704.07433/) (2017)
- [Online Batch Selection for Faster Training of Neural Networks](https://mlsanity.com/paper/1511.06343/) (2015)
- [The Emerging Trends of Multi-Label Learning](https://mlsanity.com/paper/2011.11197/) (2020)
- [Cross-Modality Attention with Semantic Graph Embedding for Multi-Label Classification](https://mlsanity.com/paper/1912.07872/) (2019)
- [LightXML: Transformer with Dynamic Negative Sampling for High-Performance Extreme Multi-label Text Classification](https://mlsanity.com/paper/2101.03305/) (2021)
- [Hard Sample Aware Network for Contrastive Deep Graph Clustering](https://mlsanity.com/paper/2212.08665/) (2022)
- [Deep Semantic Dictionary Learning for Multi-label Image Classification](https://mlsanity.com/paper/2012.12509/) (2020)
- [Carpe Diem, Seize the Samples Uncertain "At the Moment" for Adaptive Batch Selection](https://mlsanity.com/paper/1911.08050/) (2019)
- [HOT-VAE: Learning High-Order Label Correlation for Multi-Label Classification via Attention-Based Variational Autoencoders](https://mlsanity.com/paper/2103.06375/) (2021)
- [Compositional Generalization for Multi-label Text Classification: A Data-Augmentation Approach](https://mlsanity.com/paper/2312.11276/) (2023)
- [Multi-Label Adaptive Batch Selection by Highlighting Hard and Imbalanced Samples](https://mlsanity.com/paper/2403.18192/) (2024)

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

- [A Multivariate Bernoulli-Based Sampling Method for Multi-Label Data with Application to Meta-Research](https://mlsanity.com/paper/2512.08371/) (2025)
- [The Semantic Architect: How FEAML Bridges Structured Data and LLMs for Multi-Label Tasks](https://mlsanity.com/paper/2512.15082/) (2025)
- [D2ACE: Multi-Label Batch Selection Guided by Dual Dynamics and Adaptive Correlation Enhancement](https://mlsanity.com/paper/2605.09400/) (2026)
- [Addressing Imbalance in Multi-Label Data via Label-Specific Distance-based Oversampling](https://mlsanity.com/paper/2606.05927/) (2026)

## Abstract (arXiv)

The accuracy of deep neural networks is significantly influenced by the effectiveness of mini-batch construction during training. In single-label scenarios, such as binary and multi-class classification tasks, it has been demonstrated that batch selection algorithms preferring samples with higher uncertainty achieve better performance than difficulty-based methods. Although there are two batch selection methods tailored for multi-label data, none of them leverage important uncertainty information. Adapting the concept of uncertainty to multi-label data is not a trivial task, since there are two issues that should be tackled. First, traditional variance or entropy-based uncertainty measures ignore fluctuations of predictions within sliding windows and the importance of the current model state. Second, existing multi-label methods do not explicitly exploit the label correlations, particularly the uncertainty-based label correlations that evolve during the training process. In this paper, we propose an uncertainty-based multi-label batch selection algorithm. It assesses uncertainty for each label by considering differences between successive predictions and the confidence of current outputs, and further leverages dynamic uncertainty-based label correlations to emphasize instances whose uncertainty is synergistically expressed across multiple labels. Empirical studies demonstrate the effectiveness of our method in improving the performance and accelerating the convergence of various multi-label deep learning models.