Fair Classification via Transformer Neural Networks: Case Study of an Educational Domain

TL;DR

This paper investigates the fairness of transformer neural networks in educational data classification, highlighting their potential to improve fairness-accuracy trade-offs compared to classical models.

Contribution

It presents a preliminary analysis of transformer models' fairness on tabular educational datasets, exploring their impact on bias and performance.

Findings

Transformer models transform tabular data into richer representations.

Fairness-accuracy trade-off varies across datasets.

Transformer models show promising fairness improvements on Law School dataset.

Abstract

Educational technologies nowadays increasingly use data and Machine Learning (ML) models. This gives the students, instructors, and administrators support and insights for the optimum policy. However, it is well acknowledged that ML models are subject to bias, which raises concerns about the fairness, bias, and discrimination of using these automated ML algorithms in education and its unintended and unforeseen negative consequences. The contribution of bias during the decision-making comes from datasets used for training ML models and the model architecture. This paper presents a preliminary investigation of the fairness of transformer neural networks on the two tabular datasets: Law School and Student-Mathematics. In contrast to classical ML models, the transformer-based models transform these tabular datasets into a richer representation while solving the classification task. We use different fairness metrics for evaluation and check the trade-off between fairness and accuracy of the transformer-based models over the tabular datasets. Empirically, our approach shows impressive results regarding the trade-off between fairness and performance on the Law School dataset.