Domain-Hierarchy Adaptation via Chain of Iterative Reasoning for Few-Shot Hierarchical Text Classification
Abstract
Deep neural networks can easily lead to the over-fitting issue due to the influence of noisy labels. However, previous label correction methods for dealing with noisy labels often need expensive computation cost to achieve effectiveness and ignore the generalization ability of the model. To address these issues, in this paper, we propose a new meta-based self-correction method to achieve accurate filtering of noisy labels and to enhance the generalization ability of the label correction model. Specifically, we first investigate a new gradient score method to filter noisy labels with less computation cost, and then theoretically design a new generalization regularizer into the meta-learner and the base learner, for correcting noisy labels as well as achieving the generalization ability. Experimental results on real datasets verify the effectiveness of our proposed method in terms of different classification tasks.
Cite
Text
Ji et al. "Domain-Hierarchy Adaptation via Chain of Iterative Reasoning for Few-Shot Hierarchical Text Classification." International Joint Conference on Artificial Intelligence, 2024. doi:10.24963/ijcai.2024/698Markdown
[Ji et al. "Domain-Hierarchy Adaptation via Chain of Iterative Reasoning for Few-Shot Hierarchical Text Classification." International Joint Conference on Artificial Intelligence, 2024.](https://mlanthology.org/ijcai/2024/ji2024ijcai-domain/) doi:10.24963/ijcai.2024/698BibTeX
@inproceedings{ji2024ijcai-domain,
title = {{Domain-Hierarchy Adaptation via Chain of Iterative Reasoning for Few-Shot Hierarchical Text Classification}},
author = {Ji, Ke and Wang, Peng and Ke, Wenjun and Li, Guozheng and Liu, Jiajun and Gao, Jingsheng and Shang, Ziyu},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2024},
pages = {6315-6323},
doi = {10.24963/ijcai.2024/698},
url = {https://mlanthology.org/ijcai/2024/ji2024ijcai-domain/}
}