A Reductions Approach to Fair Classification

2018/03/06 by Alekh Agarwal, Alina Beygelzimer, Agarwal, Alekh +7 · 44 citations
Computer Science · Social Sciences · #Ethics and Social Impacts of AI #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Privacy-Preserving Technologies in Data

paper · pdf · doi:10.48550/arxiv.1803.02453

openalex publication_date 2018/03/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We present a systematic approach for achieving fairness in a binary classification setting. While we focus on two well-known quantitative definitions of fairness, our approach encompasses many other previously studied definitions as special cases. The key idea is to reduce fair classification to a sequence of cost-sensitive classification problems, whose solutions yield a randomized classifier with the lowest (empirical) error subject to the desired constraints. We introduce two reductions that work for any representation of the cost-sensitive classifier and compare favorably to prior baselines on a variety of data sets, while overcoming several of their disadvantages.

Citations

• A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting
• Learning Non-Discriminatory Predictors
• Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness
• Fairness in Criminal Justice Risk Assessments: The State of the Art
• Inherent Trade-Offs in the Fair Determination of Risk Scores

Cited by

• The Fair Lending Model: How the Longest-Running Algorithmic Fairness Programs Work in Practice
• Optimistic Feasible Search for Closed-Loop Fair Threshold Decision-Making
• Where to Intervene? Benchmarking Fairness-Aware Learning on Differentially Private Synthetic Tabular Data
• Penalized Fair Regression for Multiple Groups in Chronic Kidney Disease
• Algorithmic UDAP
• Randomized multi-class classification under system constraints: a unified approach via post-processing
• Contract-Governed Training for Earth Observation: Observed Service Agreement Graphs and Coverage-Accuracy Trade-offs
• The Effect of Enforcing Fairness on Reshaping Explanations in Machine Learning Models
• FairMT: Fairness for Heterogeneous Multi-Task Learning
• Fairness Meets Privacy: Integrating Differential Privacy and Demographic Parity in Multi-class Classification
• Optimal Fairness under Local Differential Privacy
• Adversarial Bias: Data Poisoning Attacks on Fairness
• A Dual Perspective on Decision-Focused Learning: Scalable Training via Dual-Guided Surrogates
• Happiness as a Measure of Fairness
• Toward Unifying Group Fairness Evaluation from a Sparsity Perspective
• FedPF: Accurate Target Privacy Preserving Federated Learning Balancing Fairness and Utility
• Bias Begins with Data: The FairGround Corpus for Robust and Reproducible Research on Algorithmic Fairness
• Visual Model Selection using Feature Importance Clusters in Fairness-Performance Similarity Optimized Space
• Doubly-Regressing Approach for Subgroup Fairness
• Fair Representation Learning with Controllable High Confidence Guarantees via Adversarial Inference
• Reliable and Reproducible Demographic Inference for Fairness in Face Analysis
• Fairness-Constrained Optimization Attack in Federated Learning
• Set to Be Fair: Demographic Parity Constraints for Set-Valued Classification
• Cost Efficient Fairness Audit Under Partial Feedback
• MultiFair: Multimodal Balanced Fairness-Aware Medical Classification with Dual-Level Gradient Modulation
• Fair Classification by Direct Intervention on Operating Characteristics
• Talking Trees: Reasoning-Assisted Induction of Decision Trees for Tabular Data
• Achieving Fair Skin Lesion Detection through Skin Tone Normalization and Channel Pruning
• OT-FairBoost: Optimal Transport-Guided Gradient Boosting for Fairness Regularization on Tabular Data
• A Multi-Objective Evaluation Framework for Analyzing Utility-Fairness Trade-Offs in Machine Learning Systems
• The Statistical Fairness-Accuracy Frontier
• On Optimal Steering to Achieve Exact Fairness
• CausalPre: Scalable and Effective Data Pre-Processing for Causal Fairness
• TFROM: A Two-sided Fairness-Aware Recommendation Model for Both Customers and Providers
• Sy-FAR: Symmetry-based Fair Adversarial Robustness
• Audits Under Resource, Data, and Access Constraints: Scaling Laws For Less Discriminatory Alternatives
• Applications and Challenges of Fairness APIs in Machine Learning Software
• Gaming and Cooperation in Federated Learning: What Can Happen and How to Monitor It
• Face4FairShifts: A Large Image Benchmark for Fairness and Robust Learning across Visual Domains
• Toward Robust Medical Fairness: Debiased Dual-Modal Alignment via Text-Guided Attribute-Disentangled Prompt Learning for Vision-Language Models
• Fairness for the People, by the People: Minority Collective Action
• Group Fairness Meets the Black Box: Enabling Fair Algorithms on Closed LLMs via Post-Processing
• Algorithmic Fairness amid Social Determinants: Reflection, Characterization, and Approach
• The Fair Game: Auditing & Debiasing AI Algorithms Over Time

Related

• The cost of fairness in classification
• Penalizing Unfairness in Binary Classification
• Minimax Optimal Fair Classification with Bounded Demographic Disparity
• Classification with Fairness Constraints: A Meta-Algorithm with Provable Guarantees
• Fairness guarantee in multi-class classification