Balancing Fairness

Balancing fairness in machine learning and related fields aims to mitigate biases and discriminatory outcomes in algorithms while maintaining accuracy and efficiency. Current research focuses on developing methods that achieve fairness through data transformations (e.g., using normalizing flows), adaptive model architectures (e.g., FairViT), and algorithmic modifications (e.g., fairness-aware boosting), often addressing the inherent trade-off between fairness and accuracy. This work is crucial for ensuring equitable outcomes in applications ranging from loan applications and hiring processes to resource allocation and environmental sustainability, impacting both the ethical development of AI and its societal impact.

19papers

Papers

March 10, 2025

You Only Debias Once: Towards Flexible Accuracy-Fairness Trade-offs at Inference Time
Fairness Accuracy Inference Time Balancing Fairness Self Debiasing

December 21, 2024

A Systems Thinking Approach to Algorithmic Fairness
Algorithmic Fairness Artificial Intelligence Policy System Approach Balancing Fairness Causal Inference

December 20, 2024

Data Preparation for Fairness-Performance Trade-Offs: A Practitioner-Friendly Alternative?
Data Preparation Previously Generated Alternative Fairness Aware Balancing Fairness Fairness Performance Trade

December 16, 2024

Fairness Shields: Safeguarding against Biased Decision Makers
Balancing Fairness Fairness Guarantee Fairness Criterion Biased Decision

November 29, 2024

Privacy-Preserving Orthogonal Aggregation for Guaranteeing Gender Fairness in Federated Recommendation
Procedural Fairness Gender Inclusive Text Balancing Fairness Group Fairness Federated Recommendation Gender Fairness Private Aggregation

September 23, 2024

AdapFair: Ensuring Continuous Fairness for Machine Learning Operations
Balancing Fairness Fairness Guarantee Downstream Classification Machine Learning Data Transformation Debiasing Method

July 20, 2024

FairViT: Fair Vision Transformer via Adaptive Masking
Adaptive Mask Vision Task Balancing Fairness Vision Transformer

June 24, 2024

Cherry on the Cake: Fairness is NOT an Optimization Problem
Procedural Fairness Balancing Fairness Optimization Problem Fairness Constraint Cake Cutting Fair Decision Multi Layered Cake

June 13, 2024

FADE: Towards Fairness-aware Augmentation for Domain Generalization via Classifier-Guided Score-based Diffusion Models
Score Based Diffusion Model Fair Synthetic Balancing Fairness Fair Machine Learning Fairness Method

March 22, 2024

Balancing Fairness and Efficiency in Energy Resource Allocations
Resource Allocation Fairness Performance Trade Balancing Fairness Fair Resource Allocation Efficient Allocation High Efficiency

March 12, 2024

Balancing Fairness and Accuracy in Data-Restricted Binary Classification
Bayes Classifier Fairness Notion Binary Classification Balancing Fairness Machine Learning Fair Decision

September 10, 2023

Exploring Social Choice Mechanisms for Recommendation Fairness in SCRUF
Social Choice Balancing Fairness Fairness Aware Recommendation Recommendation Fairness Fairness Evaluation

July 20, 2023

Fairness-Aware Client Selection for Federated Learning
Balancing Fairness Reputation System

June 1, 2023

Achieving Fairness in Multi-Agent Markov Decision Processes Using Reinforcement Learning
Reinforcement Learning Markov Decision Process Policy Gradient Multi Agent Achieving Fairness Balancing Fairness

April 12, 2023

Maximal Fairness
Fairness Notion Fairness Measure Balancing Fairness

December 13, 2022

Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without Refitting
External Influence Pre Trained Classifier Biased Training Balancing Fairness Machine Learning Model Inherent Bias Procedural Fairness

November 8, 2022

Bridging Fairness and Environmental Sustainability in Natural Language Processing
Stereotypical Bias Model Fairness Natural Language Processing Balancing Fairness FAIRness Approach Environment Optimization

July 21, 2022

FOCUS: Fairness via Agent-Awareness for Federated Learning on Heterogeneous Data
Agent Training Heterogeneous Agent Fair Federated Learning Balancing Fairness Heterogeneous Data Procedural Fairness

June 23, 2022

Context matters for fairness -- a case study on the effect of spatial distribution shifts
Case Study Procedural Fairness Temporal Shift Fairness Intervention Context Information Balancing Fairness Distribution Shift Fairness Aware Learning Mixed Effect

April 22, 2022

Balancing Fairness and Accuracy in Sentiment Detection using Multiple Black Box Models
Sentiment Analysis Balancing Fairness Black Box Model

Balancing Fairness

Papers

You Only Debias Once: Towards Flexible Accuracy-Fairness Trade-offs at Inference Time

A Systems Thinking Approach to Algorithmic Fairness

Data Preparation for Fairness-Performance Trade-Offs: A Practitioner-Friendly Alternative?

Fairness Shields: Safeguarding against Biased Decision Makers

Privacy-Preserving Orthogonal Aggregation for Guaranteeing Gender Fairness in Federated Recommendation

AdapFair: Ensuring Continuous Fairness for Machine Learning Operations

FairViT: Fair Vision Transformer via Adaptive Masking

Cherry on the Cake: Fairness is NOT an Optimization Problem

FADE: Towards Fairness-aware Augmentation for Domain Generalization via Classifier-Guided Score-based Diffusion Models

Balancing Fairness and Efficiency in Energy Resource Allocations

Balancing Fairness and Accuracy in Data-Restricted Binary Classification

Exploring Social Choice Mechanisms for Recommendation Fairness in SCRUF

Fairness-Aware Client Selection for Federated Learning

Achieving Fairness in Multi-Agent Markov Decision Processes Using Reinforcement Learning

Maximal Fairness

Fair Infinitesimal Jackknife: Mitigating the Influence of Biased Training Data Points Without Refitting

Bridging Fairness and Environmental Sustainability in Natural Language Processing

FOCUS: Fairness via Agent-Awareness for Federated Learning on Heterogeneous Data

Context matters for fairness -- a case study on the effect of spatial distribution shifts

Balancing Fairness and Accuracy in Sentiment Detection using Multiple Black Box Models