Robust Deep Graph Based Learning for Binary Classification
arXiv:1912.03321
Abstract
Convolutional neural network (CNN)-based feature learning has become state of the art, since given sufficient training data, CNN can significantly outperform traditional methods for various classification tasks. However, feature learning becomes more difficult if some training labels are noisy. With traditional regularization techniques, CNN often overfits to the noisy training labels, resulting in sub-par classification performance. In this paper, we propose a robust binary classifier, based on CNNs, to learn deep metric functions, which are then used to construct an optimal underlying graph structure used to clean noisy labels via graph Laplacian regularization (GLR). GLR is posed as a convex maximum a posteriori (MAP) problem solved via convex quadratic programming (QP). To penalize samples around the decision boundary, we propose two regularized loss functions for semi-supervised learning. The binary classification experiments on three datasets, varying in number and type of features, demonstrate that given a noisy training dataset, 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.
References in corpus (13)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Improving neural networks by preventing co-adaptation of feature detectors
- The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
- Spectral Networks and Locally Connected Networks on Graphs
- Learning to Reweight Examples for Robust Deep Learning
- Training Deep Neural Networks on Noisy Labels with Bootstrapping
- Training Convolutional Networks with Noisy Labels
- Deep Learning is Robust to Massive Label Noise
- Dynamic Graph CNN for Learning on Point Clouds
- Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noise
- Iterative Learning with Open-set Noisy Labels
- Graph Laplacian Regularized Graph Convolutional Networks for Semi-supervised Learning
- On Generalization and Regularization in Deep Learning