Fair Adversarial Networks

The influence of human judgement is ubiquitous in datasets used across the analytics industry, yet humans are known to be sub-optimal decision makers prone to various biases. Analysing biased datasets then leads to biased outcomes of the analysis. Bias by protected characteristics (e.g. race) is of particular interest as it may not only make the output of analytical process sub-optimal, but also illegal. Countering the bias by constraining the analytical outcomes to be fair is problematic because A) fairness lacks a universally accepted definition, while at the same time some definitions are mutually exclusive, and B) the use of optimisation constraints ensuring fairness is incompatible with most analytical pipelines. Both problems are solved by methods which remove bias from the data and returning an altered dataset. This approach aims to not only remove the actual bias variable (e.g. race), but also alter all proxy variables (e.g. postcode) so the bias variable is not detectable from the rest of the data. The advantage of using this approach is that the definition of fairness as a lack of detectable bias in the data (as opposed to the output of analysis) is universal and therefore solves problem (A). Furthermore, as the data is altered to remove bias the problem (B) disappears because the analytical pipelines can remain unchanged. This approach has been adopted by several technical solutions. None of them, however, seems to be satisfactory in terms of ability to remove multivariate, non-linear and non-binary biases. Therefore, in this paper I propose the concept of Fair Adversarial Networks as an easy-to-implement general method for removing bias from data. This paper demonstrates that Fair Adversarial Networks achieve this aim.

Most datasets of interest to the analytics industry are impacted by various forms of human bias. The outcomes of Data Analytics [DA] or Machine Learning [ML] on such data are therefore prone to replicating the bias. As a result, a large number of biased decision-making systems based on DA/ML have recently attracted attention. In this paper we introduce Rosa, a free, web-based tool to easily de-bias datasets with respect to a chosen characteristic. Rosa is based on the principles of Fair Adversarial Networks, developed by illumr Ltd., and can therefore remove interactive, non-linear, and non-binary bias. Rosa is stand-alone pre-processing step / API, meaning it can be used easily with any DA/ML pipeline. We test the efficacy of Rosa in removing bias from data-driven decision making systems by performing standard DA tasks on five real-world datasets, selected for their relevance to current DA problems, and also their high potential for bias. We use simple ML models to model a characteristic of analytical interest, and compare the level of bias in the model output both with and without Rosa as a pre-processing step. We find that in all cases there is a substantial decrease in bias of the data-driven decision making systems when the data is pre-processed with Rosa.

With the rapid development of deep learning, AI systems are being used more in complex and important domains and necessitates the simultaneous fulfillment of multiple constraints: accurate, robust, and fair. Accuracy measures how well a DNN can generalize to new data. Robustness demonstrates how well the network can withstand minor perturbations without changing the results. Fairness focuses on treating different groups equally. This survey provides an overview of the triangular trade-off among robustness, accuracy, and fairness in neural networks. This trade-off makes it difficult for AI systems to achieve true intelligence and is connected to generalization, robustness, and fairness in deep learning. The survey explores these trade-offs and their relationships to adversarial examples, adversarial training, and fair machine learning. The trade-offs between accuracy and robustness, accuracy and fairness, and robustness and fairness have been studied to different extents. However, there is a lack of taxonomy and analysis of these trade-offs. The accuracy-robustness trade-off is inherent in Gaussian models, but it varies when classes are not closely distributed. The accuracy-fairness and robustness-fairness trade-offs have been assessed empirically, but their theoretical nature needs more investigation. This survey aims to explore the origins, evolution, influencing factors, and future research directions of these trade-offs.

Synthetic data generation offers a promising solution to enhance the usefulness of Electronic Healthcare Records (EHR) by generating realistic de-identified data. However, the existing literature primarily focuses on the quality of synthetic health data, neglecting the crucial aspect of fairness in downstream predictions. Consequently, models trained on synthetic EHR have faced criticism for producing biased outcomes in target tasks. These biases can arise from either spurious correlations between features or the failure of models to accurately represent sub-groups. To address these concerns, we present Bias-transforming Generative Adversarial Networks (Bt-GAN), a GAN-based synthetic data generator specifically designed for the healthcare domain. In order to tackle spurious correlations (i), we propose an information-constrained Data Generation Process (DGP) that enables the generator to learn a fair deterministic transformation based on a well-defined notion of algorithmic fairness. To overcome the challenge of capturing exact sub-group representations (ii), we incentivize the generator to preserve sub-group densities through score-based weighted sampling. This approach compels the generator to learn from underrepresented regions of the data manifold. To evaluate the effectiveness of our proposed method, we conduct extensive experiments using the Medical Information Mart for Intensive Care (MIMIC-III) database. Our results demonstrate that Bt-GAN achieves state-of-the-art accuracy while significantly improving fairness and minimizing bias amplification. Furthermore, we perform an in-depth explainability analysis to provide additional evidence supporting the validity of our study. In conclusion, our research introduces a novel and professional approach to addressing the limitations of synthetic data generation in the healthcare domain. By incorporating fairness considerations and leveraging advanced techniques such as GANs, we pave the way for more reliable and unbiased predictions in healthcare applications.