FREDIS: A Fusion Framework of Refinement and Disambiguation for Unreliable Partial Label Learning

Congyu Qiao, Ning Xu, Jiaqi Lv, Yi Ren, Xin Geng
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:28321-28336, 2023.

Abstract

To reduce the difficulty of annotation, partial label learning (PLL) has been widely studied, where each example is ambiguously annotated with a set of candidate labels instead of the exact correct label. PLL assumes that the candidate label set contains the correct label, which induces disambiguation, i.e., identification of the correct label in the candidate label set, adopted in most PLL methods. However, this assumption is impractical as no one could guarantee the existence of the correct label in the candidate label set under real-world scenarios. Therefore, Unreliable Partial Label Learning (UPLL) is investigated where the correct label of each example may not exist in the candidate label set. In this paper, we propose a fusion framework of refinement and disambiguation named FREDIS to handle the UPLL problem. Specifically, with theoretical guarantees, not only does disambiguation move incorrect labels from candidate labels to non-candidate labels but also refinement, an opposite procedure, moves correct labels from non-candidate labels to candidate labels. Besides, we prove that the classifier trained by our framework could eventually approximate the Bayes optimal classifier. Extensive experiments on widely used benchmark datasets validate the effectiveness of our proposed framework.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-qiao23b, title = {{FREDIS}: A Fusion Framework of Refinement and Disambiguation for Unreliable Partial Label Learning}, author = {Qiao, Congyu and Xu, Ning and Lv, Jiaqi and Ren, Yi and Geng, Xin}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {28321--28336}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/qiao23b/qiao23b.pdf}, url = {https://proceedings.mlr.press/v202/qiao23b.html}, abstract = {To reduce the difficulty of annotation, partial label learning (PLL) has been widely studied, where each example is ambiguously annotated with a set of candidate labels instead of the exact correct label. PLL assumes that the candidate label set contains the correct label, which induces disambiguation, i.e., identification of the correct label in the candidate label set, adopted in most PLL methods. However, this assumption is impractical as no one could guarantee the existence of the correct label in the candidate label set under real-world scenarios. Therefore, Unreliable Partial Label Learning (UPLL) is investigated where the correct label of each example may not exist in the candidate label set. In this paper, we propose a fusion framework of refinement and disambiguation named FREDIS to handle the UPLL problem. Specifically, with theoretical guarantees, not only does disambiguation move incorrect labels from candidate labels to non-candidate labels but also refinement, an opposite procedure, moves correct labels from non-candidate labels to candidate labels. Besides, we prove that the classifier trained by our framework could eventually approximate the Bayes optimal classifier. Extensive experiments on widely used benchmark datasets validate the effectiveness of our proposed framework.} }
Endnote
%0 Conference Paper %T FREDIS: A Fusion Framework of Refinement and Disambiguation for Unreliable Partial Label Learning %A Congyu Qiao %A Ning Xu %A Jiaqi Lv %A Yi Ren %A Xin Geng %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-qiao23b %I PMLR %P 28321--28336 %U https://proceedings.mlr.press/v202/qiao23b.html %V 202 %X To reduce the difficulty of annotation, partial label learning (PLL) has been widely studied, where each example is ambiguously annotated with a set of candidate labels instead of the exact correct label. PLL assumes that the candidate label set contains the correct label, which induces disambiguation, i.e., identification of the correct label in the candidate label set, adopted in most PLL methods. However, this assumption is impractical as no one could guarantee the existence of the correct label in the candidate label set under real-world scenarios. Therefore, Unreliable Partial Label Learning (UPLL) is investigated where the correct label of each example may not exist in the candidate label set. In this paper, we propose a fusion framework of refinement and disambiguation named FREDIS to handle the UPLL problem. Specifically, with theoretical guarantees, not only does disambiguation move incorrect labels from candidate labels to non-candidate labels but also refinement, an opposite procedure, moves correct labels from non-candidate labels to candidate labels. Besides, we prove that the classifier trained by our framework could eventually approximate the Bayes optimal classifier. Extensive experiments on widely used benchmark datasets validate the effectiveness of our proposed framework.
APA
Qiao, C., Xu, N., Lv, J., Ren, Y. & Geng, X.. (2023). FREDIS: A Fusion Framework of Refinement and Disambiguation for Unreliable Partial Label Learning. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:28321-28336 Available from https://proceedings.mlr.press/v202/qiao23b.html.

Related Material