paper-with-me

Papers

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

2026-05-10 · Bin Liu, Haoyu Peng, Zhijia Wei, Jiajing Zhang, Grigorios Tsoumakas 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.

📄 PDF Abstract BibTeX arXiv:2605.09400

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Label Classification

Similar Papers 제목 키워드 기반

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

2024-12-21 · Ao Zhou, Bin Liu, Jin Wang, Grigorios Tsoumakas

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 bee…

Multi-class ClassificationMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATION

Discriminative Batch Mode Active Learning

2007-12-01 · NeurIPS 2007 12 · Yuhong Guo, Dale Schuurmans

Active learning sequentially selects unlabeled instances to label with the goal of reducing the effort needed to learn a good classifier. Most previous studies in active learning have focused on selecting one unlabeled i…

Active Learning

A-SFS: Semi-supervised Feature Selection based on Multi-task Self-supervision

2022-07-19 · Zhifeng Qiu, Wanxin Zeng, Dahua Liao, Ning Gui

Feature selection is an important process in machine learning. It builds an interpretable and robust model by selecting the features that contribute the most to the prediction target. However, most mature feature selecti…

feature selectionSelf-Supervised Learning

Multi-Label Adaptive Batch Selection by Highlighting Hard and Imbalanced Samples

2024-03-27 · Ao Zhou, Bin Liu, Jin Wang, Grigorios Tsoumakas

Deep neural network models have demonstrated their effectiveness in classifying multi-label data from various domains. Typically, they employ a training mode that combines mini-batches with optimizers, where each sample …

Labeled TrustSet Guided: Batch Active Learning with Reinforcement Learning

2026-04-14 · Guofeng Cui, Yang Liu, Pichao Wang, Hankai Hsu 외 arxiv

Batch active learning (BAL) is a crucial technique for reducing labeling costs and improving data efficiency in training large-scale deep learning models. Traditional BAL methods often rely on metrics like Mahalanobis Di…

Reinforcement LearningImage ClassificationActive Learning