UnbiasedNets: A Dataset Diversification Framework for Robustness Bias Alleviation in Neural Networks

Abstract

Performance of trained neural network (NN) models, in terms of testing accuracy, has improved remarkably over the past several years, especially with the advent of deep learning. However, even the most accurate NNs can be biased toward a specific output classification due to the inherent bias in the available training datasets, which may propagate to the real-world implementations. This paper deals with the robustness bias, i.e., the bias exhibited by the trained NN by having a significantly large robustness to noise for a certain output class, as compared to the remaining output classes. The bias is shown to result from imbalanced datasets, i.e., the datasets where all output classes are not equally represented. Towards this, we propose the UnbiasedNets framework, which leverages K-means clustering and the NN's noise tolerance to diversify the given training dataset, even from relatively smaller datasets. This generates balanced datasets and reduces the bias within the datasets themselves. To the best of our knowledge, this is the first framework catering to the robustness bias problem in NNs. We use real-world datasets to demonstrate the efficacy of the UnbiasedNets for data diversification, in case of both binary and multi-label classifiers. The results are compared to well-known tools aimed at generating balanced datasets, and illustrate how existing works have limited success while addressing the robustness bias. In contrast, UnbiasedNets provides a notable improvement over existing works, while even reducing the robustness bias significantly in some cases, as observed by comparing the NNs trained on the diversified and original datasets.

arXiv commentSpringer Machine Learning 2023

References in corpus (15)

• SMOTE: Synthetic Minority Over-sampling Technique
• Explaining and Harnessing Adversarial Examples
• A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation
• Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning
• DeepXplore: Automated Whitebox Testing of Deep Learning Systems
• Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systems
• Adversarial Filters of Dataset Biases
• Learning from others' mistakes: Avoiding dataset biases without modeling them
• Parallelization Techniques for Verifying Neural Networks
• To be Robust or to be Fair: Towards Fairness in Adversarial Training
• Removing Bias in Multi-modal Classifiers: Regularization by Maximizing Functional Entropies
• Robustness May Be at Odds with Fairness: An Empirical Study on Class-wise Accuracy
• Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning
• Intra-Processing Methods for Debiasing Neural Networks
• Fair SA: Sensitivity Analysis for Fairness in Face Recognition