Multi-label classification poses challenges due to imbalanced and noisy labels in training data. 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.
@article{arxiv.2312.07087,
title = {Toward Robustness in Multi-label Classification: A Data Augmentation Strategy against Imbalance and Noise},
author = {Hwanjun Song and Minseok Kim and Jae-Gil Lee},
journal= {arXiv preprint arXiv:2312.07087},
year = {2023}
}
Comments
This paper was accepted at AAAI 2024. We upload the full version of our paper on arXiv due to the page limit of AAAI