Distraction is All You Need For Fairness

Mehdi Yazdani-Jahromi, Amirarsalan Rajabi, aida Tayebi, Ozlem Garibay

Keywords: Fairness, Deep Learning, Neural Networks, Adversarial Learning

Abstract:

Bias in training datasets must be managed for various groups in classification tasks
to ensure parity or equal treatment. With the recent growth in artificial intelli-
gence models and their expanding role in automated decision-making, ensuring
that these models are not biased is vital. There is an abundance of evidence sug-
gesting that these models could contain or even amplify the bias present in the
data on which they are trained, inherent to their objective function and learning
algorithms; Many researchers direct their attention to this issue in different direc-
tions, namely, changing data to be statistically independent, adversarial training
for restricting the capabilities of a particular competitor who aims to maximize
parity, etc. These methods result in information loss and do not provide a suitable
balance between accuracy and fairness or do not ensure limiting the biases in train-
ing. To this end, we propose a powerful strategy for training deep learning models
called the Distraction module, which can be theoretically proven effective in con-
trolling bias from affecting the classification results. This method can be utilized
with different data types (e.g., Tabular, images, graphs, etc.). We demonstrate the
potency of the proposed method by testing it on UCI Adult and Heritage Health
datasets (tabular), POKEC-Z, POKEC-N and NBA datasets (graph), and CelebA
dataset (Vision). Using state-of-the-art methods proposed in the fairness literature
for each dataset, we exhibit our model is superior to these proposed methods in
minimizing bias and maintaining accuracy.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Social Aspects of Machine Learning (eg, AI safety, fairness, privacy, interpretability, human-AI interaction, ethics)