AAAI 2024technical7 citations
Toward Robustness in Multi-Label Classification: A Data Augmentation Strategy against Imbalance and Noise
Hwanjun Song, Minseok Kim, Jae-Gil Lee
Abstract
Multi-label classification poses challenges due to imbalanced and noisy labels in training data. In this paper, we propose a unified data augmentation method, named BalanceMix, to address these challenges. Our approach includes two samplers for imbalanced labels, generating minority-augmented instances with high diversity. It also refines multi-labels at the label-wise granularity, categorizing noisy labels as clean, re-labeled, or ambiguous for robust optimization. Extensive experiments on three benchmark datasets demonstrate that BalanceMix outperforms existing state-of-the-art methods. We release the code at https://github.com/DISL-Lab/BalanceMix.
BibTeX
@article{Song_Kim_Lee_2024, title={Toward Robustness in Multi-Label Classification: A Data Augmentation Strategy against Imbalance and Noise}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/30157}, DOI={10.1609/aaai.v38i19.30157}, abstractNote={Multi-label classification poses challenges due to imbalanced and noisy labels in training data. In this paper, we propose a unified data augmentation method, named BalanceMix, to address these challenges. Our approach includes two samplers for imbalanced labels, generating minority-augmented instances with high diversity. It also refines multi-labels at the label-wise granularity, categorizing noisy labels as clean, re-labeled, or ambiguous for robust optimization. Extensive experiments on three benchmark datasets demonstrate that BalanceMix outperforms existing state-of-the-art methods. We release the code at https://github.com/DISL-Lab/BalanceMix.}, number={19}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Song, Hwanjun and Kim, Minseok and Lee, Jae-Gil}, year={2024}, month={Mar.}, pages={21592-21601} }