From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model
This addresses the issue of noisy labels for machine learning practitioners by providing a post-hoc correction method, though it is incremental as it builds on transition matrix-based approaches.
The paper tackles the problem of noisy labels in machine learning by introducing Noisy Prediction Calibration (NPC), a post-processing method that uses a generative model to correct predictions from pre-trained classifiers, resulting in improved classification performance on synthetic and real-world datasets.
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.