A Study of Deep CNN Model with Labeling Noise Based on Granular-ball Computing

TL;DR

This paper introduces a granular ball neural network model that effectively filters label noise during training, enhancing the robustness of deep CNNs against noisy labels in supervised learning.

Contribution

It pioneers a multi-granular approach based on granular computing to reduce label noise impact in deep neural networks, improving model stability and accuracy.

Findings

Reduces label noise proportion in training data

Improves neural network robustness against label noise

Enhances model stability during training

Abstract

In supervised learning, the presence of noise can have a significant impact on decision making. Since many classifiers do not take label noise into account in the derivation of the loss function, including the loss functions of logistic regression, SVM, and AdaBoost, especially the AdaBoost iterative algorithm, whose core idea is to continuously increase the weight value of the misclassified samples, the weight of samples in many presence of label noise will be increased, leading to a decrease in model accuracy. In addition, the learning process of BP neural network and decision tree will also be affected by label noise. Therefore, solving the label noise problem is an important element of maintaining the robustness of the network model, which is of great practical significance. Granular ball computing is an important modeling method developed in the field of granular computing in recent years, which is an efficient, robust and scalable learning method. In this paper, we pioneered a granular ball neural network algorithm model, which adopts the idea of multi-granular to filter label noise samples during model training, solving the current problem of model instability caused by label noise in the field of deep learning, greatly reducing the proportion of label noise in training samples and improving the robustness of neural network models.