Learning Fair Rule Lists

2019/09/09 by Ulrich Aïvodji, Julien Ferry, Aïvodji, Ulrich +8 · 7 citations
Computer Science · Mathematics · Social Sciences · #Adversarial Robustness in Machine Learning #Artificial intelligence #Black box #Computer science #Data mining #Decision rule #Ethics and Social Impacts of AI #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Logistic regression #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine learning #Odds #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.1909.03977

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2019/09/09 · arxiv created 2020/02/18 · arxiv updated 2020/02/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

As the use of black-box models becomes ubiquitous in high stake decision-making systems, demands for fair and interpretable models are increasing. While it has been shown that interpretable models can be as accurate as black-box models in several critical domains, existing fair classification techniques that are interpretable by design often display poor accuracy/fairness tradeoffs in comparison with their non-interpretable counterparts. In this paper, we propose FairCORELS, a fair classification technique interpretable by design, whose objective is to learn fair rule lists. Our solution is a multi-objective variant of CORELS, a branch-and-bound algorithm to learn rule lists, that supports several statistical notions of fairness. Examples of such measures include statistical parity, equal opportunity and equalized odds. The empirical evaluation of FairCORELS on real-world datasets demonstrates that it outperforms state-of-the-art fair classification techniques that are interpretable by design while being competitive with non-interpretable ones.

Citations

• Certifying and Removing Disparate Impact
• Fairness through awareness
• On the relation between accuracy and fairness in binary classification
• European Union regulations on algorithmic decision-making and a "right to explanation"
• Equality of Opportunity in Supervised Learning
• Grad-CAM: Why did you say that?
• Feature Importance Measure for Non-linear Learning Algorithms
• Towards A Rigorous Science of Interpretable Machine Learning
• Fairness in Criminal Justice Risk Assessments: The State of the Art
• Methods for Interpreting and Understanding Deep Neural Networks
• Counterfactual Fairness
• Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness
• Boolean Decision Rules via Column Generation
• The Frontiers of Fairness in Machine Learning
• Learning Optimal and Fair Decision Trees for Non-Discriminative Decision-Making
• Explanations can be manipulated and geometry is to blame
• FAHT: An Adaptive Fairness-aware Decision Tree Classifier
• A Survey Of Methods For Explaining Black Box Models
• Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
• Inherent Trade-Offs in the Fair Determination of Risk Scores
• The Bouncer Problem: Challenges to Remote Explainability
• Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods

Related

• Fairwashing: the risk of rationalization
• FARE: Provably Fair Representation Learning with Practical Certificates
• Through the Data Management Lens: Experimental Analysis and Evaluation of Fair Classification
• Fairness Warnings and Fair-MAML: Learning Fairly with Minimal Data
• Fairness Interventions in Classification: A Study on AI Explainability