2022/03/15 by Mehdi Yazdani-Jahromi, Amirarsalan Rajabi, Yazdani-Jahromi, Mehdi +6 · 2 citations
Computer Science · Medicine · Social Sciences · #Artificial Intelligence (cs.AI) #Artificial Intelligence in Healthcare and Education #Artificial intelligence #Computer science #Data mining #Distraction #Ethics and Social Impacts of AI #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Graph #Labeled data #Limiting #Machine Learning (cs.LG) #Machine learning #Theoretical computer science #Training set
paper · pdf · doi:10.48550/arxiv.2203.07593
published in arXiv (Cornell University) (Cornell University)
openalex publication_date 2022/03/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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 intelligence models and their expanding role in automated decision-making, ensuring that these models are not biased is vital. There is an abundance of evidence suggesting 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 directions, 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 training. To this end, we propose a powerful strategy for training deep learning models called the Distraction module, which can be theoretically proven effective in controlling 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.