# Mitigating Algorithmic Bias in Multiclass CNN Classifications Using Causal Modeling

arXiv: https://arxiv.org/abs/2501.07885 · HTML: https://mlsanity.com/paper/2501.07885/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 17 references that are in the map.
- First posted on arXiv 14 Jan 2025.

## Builds on (most cited first, 14 of 14)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Direct and Indirect Effects](https://mlsanity.com/paper/1301.2300/) (2013)
- [Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations](https://mlsanity.com/paper/1707.00075/) (2017)
- [Classification with Fairness Constraints: A Meta-Algorithm with Provable Guarantees](https://mlsanity.com/paper/1806.06055/) (2018)
- [Fairness And Bias in Artificial Intelligence: A Brief Survey of Sources, Impacts, And Mitigation Strategies](https://mlsanity.com/paper/2304.07683/) (2023)
- [Fairness Through Causal Awareness: Learning Latent-Variable Models for Biased Data](https://mlsanity.com/paper/1809.02519/) (2018)
- [Fairness in Algorithmic Decision Making: An Excursion Through the Lens of Causality](https://mlsanity.com/paper/1903.11719/) (2019)
- [Blackbox Post-Processing for Multiclass Fairness](https://mlsanity.com/paper/2201.04461/) (2022)
- [TARA: Training and Representation Alteration for AI Fairness and Domain Generalization](https://mlsanity.com/paper/2012.06387/) (2020)
- [AI Fairness via Domain Adaptation](https://mlsanity.com/paper/2104.01109/) (2021)
- [Detecting and Mitigating Algorithmic Bias in Binary Classification using Causal Modeling](https://mlsanity.com/paper/2310.12421/) (2023)
- [Mitigating Nonlinear Algorithmic Bias in Binary Classification](https://mlsanity.com/paper/2312.05429/) (2023)

## Abstract (arXiv)

This study describes a procedure for applying causal modeling to detect and mitigate algorithmic bias in a multiclass classification problem. The dataset was derived from the FairFace dataset, supplemented with emotional labels generated by the DeepFace pre-trained model. A custom Convolutional Neural Network (CNN) was developed, consisting of four convolutional blocks, followed by fully connected layers and dropout layers to mitigate overfitting. Gender bias was identified in the CNN model's classifications: Females were more likely to be classified as "happy" or "sad," while males were more likely to be classified as "neutral." To address this, the one-vs-all (OvA) technique was applied. A causal model was constructed for each emotion class to adjust the CNN model's predicted class probabilities. The adjusted probabilities for the various classes were then aggregated by selecting the class with the highest probability. The resulting debiased classifications demonstrated enhanced gender fairness across all classes, with negligible impact--or even a slight improvement--on overall accuracy. This study highlights that algorithmic fairness and accuracy are not necessarily trade-offs. All data and code for this study are publicly available for download.