# D2ACE: Multi-Label Batch Selection Guided by Dual Dynamics and Adaptive Correlation Enhancement

arXiv: https://arxiv.org/abs/2605.09400 · HTML: https://mlsanity.com/paper/2605.09400/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 43 references that are in the map.
- First posted on arXiv 10 May 2026.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [An Empirical Study of Example Forgetting during Deep Neural Network Learning](https://mlsanity.com/paper/1812.05159/) (2018)
- [Multi-Label Image Recognition with Graph Convolutional Networks](https://mlsanity.com/paper/1904.03582/) (2019)
- [Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samples](https://mlsanity.com/paper/1704.07433/) (2017)
- [General Multi-label Image Classification with Transformers](https://mlsanity.com/paper/2011.14027/) (2020)
- [A Sufficient Condition for Convergences of Adam and RMSProp](https://mlsanity.com/paper/1811.09358/) (2018)
- [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)
- [Texts as Images in Prompt Tuning for Multi-Label Image Recognition](https://mlsanity.com/paper/2211.12739/) (2022)
- [Characterizing Datapoints via Second-Split Forgetting](https://mlsanity.com/paper/2210.15031/) (2022)
- [Heterogeneous Semantic Transfer for Multi-label Recognition with Partial Labels](https://mlsanity.com/paper/2205.11131/) (2022)
- [Deep Learning for Multi-Label Learning: A Comprehensive Survey](https://mlsanity.com/paper/2401.16549/) (2024)
- [TAI++: Text as Image for Multi-Label Image Classification by Co-Learning Transferable Prompt](https://mlsanity.com/paper/2405.06926/) (2024)
- [Multi-Label Learning with Deep Forest](https://mlsanity.com/paper/1911.06557/) (2019)
- [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)
- [An Effective Deployment of Contrastive Learning in Multi-label Text Classification](https://mlsanity.com/paper/2212.00552/) (2022)
- [Positive Label Is All You Need for Multi-Label Classification](https://mlsanity.com/paper/2306.16016/) (2023)
- [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)
- [Batch Selection for Multi-Label Classification Guided by Uncertainty and Dynamic Label Correlations](https://mlsanity.com/paper/2412.16521/) (2024)
- [AEMLO: AutoEncoder-Guided Multi-Label Oversampling](https://mlsanity.com/paper/2408.13078/) (2024)

## Abstract (arXiv)

Batch selection is crucial for improving both training efficiency and predictive performance in deep multi-label classification (MLC). Existing batch selection methods typically rely on a single metric to assess instance importance and use static label weights to distinguish label significance, neglecting the dynamic evolution of metric utility and label significance during training. In addition, the method that explicitly exploits label correlations is largely affected by abundant irrelevant labels and insensitive to local label distributions. To address these issues, we propose D2ACE, a novel multi-label batch selection method guided by Dual Dynamics and Adaptive Correlation Enhancement. D2ACE explicitly captures metric and label-level training dynamics by combining stage-wise Bernoulli mixture sampling, which balances uncertainty and noise-resistant hardness, with dynamic label weighting to recalibrate label priorities at each epoch based on current metric statistics. Furthermore, D2ACE introduces a local context-aware correlation enhancement to focus on relevant labels with instance-adaptive dependencies. Extensive experiments on tabular and image benchmarks demonstrate that D2ACE outperforms existing batch selection approaches across various deep MLC models, achieving stronger predictive performance and more efficient correlation modeling.