ULAREF: A Unified Label Refinement Framework for Learning with Inaccurate Supervision

Congyu Qiao, Ning Xu, Yihao Hu, Xin Geng
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:41456-41472, 2024.

Abstract

Learning with inaccurate supervision is often encountered in weakly supervised learning, and researchers have invested a considerable amount of time and effort in designing specialized algorithms for different forms of annotations in inaccurate supervision. In fact, different forms of these annotations share the fundamental characteristic that they all still incorporate some portion of correct labeling information. This commonality can serve as a lever, enabling the creation of a cohesive framework designed to tackle the challenges associated with various forms of annotations in learning with inaccurate supervision. In this paper, we propose a unified label refinement framework named ULAREF, i.e., a Unified LAbel REfinement Framework for learning with inaccurate supervision, which is capable of leveraging label refinement to handle inaccurate supervision. Specifically, our framework trains the predictive model with refined labels through global detection of reliability and local enhancement using an enhanced model fine-tuned by a proposed consistency loss. Also, we theoretically justify that the enhanced model in local enhancement can achieve higher accuracy than the predictive model on the detected unreliable set under mild assumptions.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-qiao24c, title = {{ULAREF}: A Unified Label Refinement Framework for Learning with Inaccurate Supervision}, author = {Qiao, Congyu and Xu, Ning and Hu, Yihao and Geng, Xin}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {41456--41472}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/qiao24c/qiao24c.pdf}, url = {https://proceedings.mlr.press/v235/qiao24c.html}, abstract = {Learning with inaccurate supervision is often encountered in weakly supervised learning, and researchers have invested a considerable amount of time and effort in designing specialized algorithms for different forms of annotations in inaccurate supervision. In fact, different forms of these annotations share the fundamental characteristic that they all still incorporate some portion of correct labeling information. This commonality can serve as a lever, enabling the creation of a cohesive framework designed to tackle the challenges associated with various forms of annotations in learning with inaccurate supervision. In this paper, we propose a unified label refinement framework named ULAREF, i.e., a Unified LAbel REfinement Framework for learning with inaccurate supervision, which is capable of leveraging label refinement to handle inaccurate supervision. Specifically, our framework trains the predictive model with refined labels through global detection of reliability and local enhancement using an enhanced model fine-tuned by a proposed consistency loss. Also, we theoretically justify that the enhanced model in local enhancement can achieve higher accuracy than the predictive model on the detected unreliable set under mild assumptions.} }
Endnote
%0 Conference Paper %T ULAREF: A Unified Label Refinement Framework for Learning with Inaccurate Supervision %A Congyu Qiao %A Ning Xu %A Yihao Hu %A Xin Geng %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-qiao24c %I PMLR %P 41456--41472 %U https://proceedings.mlr.press/v235/qiao24c.html %V 235 %X Learning with inaccurate supervision is often encountered in weakly supervised learning, and researchers have invested a considerable amount of time and effort in designing specialized algorithms for different forms of annotations in inaccurate supervision. In fact, different forms of these annotations share the fundamental characteristic that they all still incorporate some portion of correct labeling information. This commonality can serve as a lever, enabling the creation of a cohesive framework designed to tackle the challenges associated with various forms of annotations in learning with inaccurate supervision. In this paper, we propose a unified label refinement framework named ULAREF, i.e., a Unified LAbel REfinement Framework for learning with inaccurate supervision, which is capable of leveraging label refinement to handle inaccurate supervision. Specifically, our framework trains the predictive model with refined labels through global detection of reliability and local enhancement using an enhanced model fine-tuned by a proposed consistency loss. Also, we theoretically justify that the enhanced model in local enhancement can achieve higher accuracy than the predictive model on the detected unreliable set under mild assumptions.
APA
Qiao, C., Xu, N., Hu, Y. & Geng, X.. (2024). ULAREF: A Unified Label Refinement Framework for Learning with Inaccurate Supervision. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:41456-41472 Available from https://proceedings.mlr.press/v235/qiao24c.html.

Related Material