.png){kind=icon}
Return
Robust Deep Graph Based Learning for Binary Classification
.png){kind=icon}
OA
AI
DOI：10.1109/TSIPN.2020.3040993.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Convolutional neural network (CNN)-based feature learning has become the state-of-the-art for many applications since, given sufficient training data, CNN can significantly outperform traditional methods for various classification tasks. However, feature learning is more challenging if training labels are noisy as CNN tends to overfit to the noisy training labels, resulting in sub-par classification performance. In this paper, we propose a robust binary classifier by learning CNN-based deep metric functions, to construct a graph, used to clean the noisy labels via graph Laplacian regularization (GLR). The denoised labels are then used in two proposed loss correction functions to regularize the deep metric functions. As a result, the node-to-node correlations in the graph are better reflected, leading to improved predictive performance. The experiments on three datasets, varying in number and type of features and under different levels of noise, demonstrate that given a noisy training dataset for the semi-supervised classification task, our proposed networks outperform several state-of-the-art classifiers, including label-noise robust support vector machine, CNNs with three different robust loss functions, model-based GLR, and dynamic graph CNN classifiers.
Keywords:
Noise measurement
Training
Laplace equations
Convolution
Support vector machines
Task analysis
Neural networks
Binary classification
graph laplacian regularization
semi-supervised learning
deep learning
Journal
IF:
4.9
Papers:
738
Citations:
1.9K
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSaveAnalysis of blasting related accidents with emphasis on flyrock and its mitigation in surface mines
PREAI
ShareSaveShareSaveShareSave
View more