2022-06-28-bae22a.md

title	booktitle	abstract	layout	series	publisher	issn	id	month	tex_title	firstpage	lastpage	page	order	cycles	bibtex_author	author	date	address	container-title	volume	genre	issued	pdf	extras
From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model	Proceedings of the 39th International Conference on Machine Learning	Noisy labels are inevitable yet problematic in machine learning society. It ruins the generalization of a classifier by making the classifier over-fitted to noisy labels. Existing methods on noisy label have focused on modifying the classifier during the training procedure. It has two potential problems. First, these methods are not applicable to a pre-trained classifier without further access to training. Second, it is not easy to train a classifier and regularize all negative effects from noisy labels, simultaneously. We suggest a new branch of method, Noisy Prediction Calibration (NPC) in learning with noisy labels. Through the introduction and estimation of a new type of transition matrix via generative model, NPC corrects the noisy prediction from the pre-trained classifier to the true label as a post-processing scheme. We prove that NPC theoretically aligns with the transition matrix based methods. Yet, NPC empirically provides more accurate pathway to estimate true label, even without involvement in classifier learning. Also, NPC is applicable to any classifier trained with noisy label methods, if training instances and its predictions are available. Our method, NPC, boosts the classification performances of all baseline models on both synthetic and real-world datasets. The implemented code is available at https://github.com/BaeHeeSun/NPC.	inproceedings	Proceedings of Machine Learning Research	PMLR	2640-3498	bae22a	0	From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model	1277	1297	1277-1297	1277	false	Bae, Heesun and Shin, Seungjae and Na, Byeonghu and Jang, Joonho and Song, Kyungwoo and Moon, Il-Chul	given family Heesun Bae given family Seungjae Shin given family Byeonghu Na given family Joonho Jang given family Kyungwoo Song given family Il-Chul Moon	2022-06-28		Proceedings of the 39th International Conference on Machine Learning	162	inproceedings	date-parts 2022 6 28	https://proceedings.mlr.press/v162/bae22a/bae22a.pdf