Bias-Resilient Neural Network

10/08/2019
by   Ehsan Adeli, et al.
22

Presence of bias and confounding effects is inarguably one of the most critical challenges in machine learning applications that has alluded to pivotal debates in the recent years. Such challenges range from spurious associations of confounding variables in medical studies to the bias of race in gender or face recognition systems. One solution is to enhance datasets and organize them such that they do not reflect biases, which is a cumbersome and intensive task. The alternative is to make use of available data and build models considering these biases. Traditional statistical methods apply straightforward techniques such as residualization or stratification to precomputed features to account for confounding variables. However, these techniques are generally not suitable for end-to-end deep learning methods. In this paper, we propose a method based on the adversarial training strategy to learn discriminative features unbiased and invariant to the confounder(s). This is enabled by incorporating a new adversarial loss function that encourages a vanished correlation between the bias and learned features. We apply our method to synthetic data, medical images, and a gender classification (Gender Shades Pilot Parliaments Benchmark) dataset. Our results show that the learned features by our method not only result in superior prediction performance but also are uncorrelated with the bias or confounder variables. The code is available at http://github.com/QingyuZhao/BR-Net/.

READ FULL TEXT

page 2

page 4

page 7

research
10/28/2020

Image Representations Learned With Unsupervised Pre-Training Contain Human-like Biases

Recent advances in machine learning leverage massive datasets of unlabel...
research
12/12/2019

It's easy to fool yourself: Case studies on identifying bias and confounding in bio-medical datasets

Confounding variables are a well known source of nuisance in biomedical ...
research
04/18/2018

Modeling and Simultaneously Removing Bias via Adversarial Neural Networks

In real world systems, the predictions of deployed Machine Learned model...
research
10/28/2020

Raw Audio for Depression Detection Can Be More Robust Against Gender Imbalance than Mel-Spectrogram Features

Depression is a large-scale mental health problem and a challenging area...
research
10/28/2021

XDEEP-MSI: Explainable Bias-Rejecting Microsatellite Instability Deep Learning System In Colorectal Cancer

We present a system for the prediction of microsatellite instability (MS...
research
05/20/2020

Risk of Training Diagnostic Algorithms on Data with Demographic Bias

One of the critical challenges in machine learning applications is to ha...
research
04/26/2023

Multimodal Composite Association Score: Measuring Gender Bias in Generative Multimodal Models

Generative multimodal models based on diffusion models have seen tremend...

Please sign up or login with your details

Forgot password? Click here to reset