Fairness Implication

Fairness implications in machine learning (ML) research focus on mitigating biases that lead to discriminatory outcomes across different demographic groups. Current research investigates how various factors, from data preprocessing and model architecture choices (including transformers and ensemble methods) to the definition of target variables and even hardware selection, influence fairness metrics. This work is crucial for ensuring responsible and equitable deployment of ML systems across diverse applications, impacting both the development of fairer algorithms and the ethical considerations surrounding their use.

Papers

October 10, 2024

No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users
Mengxuan Hu, Hongyi Wu, Zihan Guan, Ronghang Zhu, Dongliang Guo, Daiqing Qi, Sheng Li
Large Language Model Retrieval Augmented Generation Free Lunch Fairness Implication Robust Fairness

August 19, 2024

Strategic Demonstration Selection for Improved Fairness in LLM In-Context Learning
Jingyu Hu, Weiru Liu, Mengnan Du
Large Language Model Context Learning LLM in Context Minority Sample Fairness Implication Demonstration Selection

June 10, 2024

Long-Term Fairness Inquiries and Pursuits in Machine Learning: A Survey of Notions, Methods, and Challenges
Usman Gohar, Zeyu Tang, Jialu Wang, Kun Zhang, Peter L. Spirtes, Yang Liu, Lu Cheng
Machine Learning Timely Survey Technical Challenge Fairness Assessment Long Term Fairness Fairness Criterion Fairness Implication

March 9, 2024

FairTargetSim: An Interactive Simulator for Understanding and Explaining the Fairness Effects of Target Variable Definition
Dalia Gala, Milo Phillips-Brown, Naman Goel, Carinal Prunkl, Laura Alvarez Jubete, medb corcoran, Ray Eitel-Porter
Machine Learning Procedural Fairness Human Understanding Interactive Simulation Fairness Implication Target Variable

January 16, 2024

The Impact of Differential Feature Under-reporting on Algorithmic Fairness
Nil-Jana Akpinar, Zachary C. Lipton, Alexandra Chouldechova
Artificial Intelligence Global Impact Algorithmic Fairness Risk Prediction Fairness Implication

December 6, 2023

On The Fairness Impacts of Hardware Selection in Machine Learning
Sree Harsha Nelaturu, Nishaanth Kanna Ravichandran, Cuong Tran, Sara Hooker, Ferdinando Fioretto
Machine Learning Gradient Flow Model Performance Fairness Implication Hardware Design Optimization

September 2, 2023

Fairness Implications of Heterogeneous Treatment Effect Estimation with Machine Learning Methods in Policy-making
Patrick Rehill, Nicholas Biddle
Machine Learning AI Fairness Causal Machine Learning Causal Machine Fairness Implication Heterogeneous Treatment Effect Estimation

August 31, 2023

One Model Many Scores: Using Multiverse Analysis to Prevent Fairness Hacking and Evaluate the Influence of Model Design Decisions
Jan Simson, Florian Pfisterer, Christoph Kern
External Influence Algorithmic Fairness Fairness Implication Fairness Attack Model Decision

May 19, 2023

On the Fairness Impacts of Private Ensembles Models
Cuong Tran, Ferdinando Fioretto
Differential Privacy Semi Supervised Private Model Private Aggregation Fairness Implication Ensemble Teacher Private Ensemble

May 11, 2023

A Survey on Intersectional Fairness in Machine Learning: Notions, Mitigation, and Challenges
Usman Gohar, Lu Cheng
Machine Learning Timely Survey Technical Challenge Procedural Fairness Intersectional Bias Fairness Implication Intersectional Fairness Intersectional Social Attribute

February 8, 2023

Mitigating Bias in Visual Transformers via Targeted Alignment
Sruthi Sudhakar, Viraj Prabhu, Arvindkumar Krishnakumar, Judy Hoffman
Vision Transformer Computer Vision Transformer Architecture Mitigating Bias Fairness Implication

July 22, 2022

Algorithmic Fairness in Business Analytics: Directions for Research and Practice
Maria De-Arteaga, Stefan Feuerriegel, Maytal Saar-Tsechansky
DH Research Practice Mode Algorithmic Fairness Interpretable Direction Fairness Implication Business Intelligence

May 31, 2022

Bias-inducing geometries: an exactly solvable data model with fairness implications
Stefano Sarao Mannelli, Federica Gerace, Negar Rostamzadeh, Luca Saglietti
Bias Mitigation Data Imbalance Fairness Accuracy Fairness Implication Data Model

May 9, 2022

Evaluating the Fairness Impact of Differentially Private Synthetic Data
Blake Bullwinkel, Kristen Grabarz, Lily Ke, Scarlett Gong, Chris Tanner, Joshua Allen
Synthetic Data Procedural Fairness Multi Label Downstream Classification Fairness Implication

April 21, 2022

A Sandbox Tool to Bias(Stress)-Test Fairness Algorithms
Nil-Jana Akpinar, Manish Nagireddy, Logan Stapleton, Hao-Fei Cheng, Haiyi Zhu, Steven Wu, Hoda Heidari
Bias Evaluation Fairness Intervention FAIrness Testing Fairness Implication Sandbox Environment

January 27, 2022

Fairness Implications of Encoding Protected Categorical Attributes
Carlos Mougan, Jose M. Alvarez, Salvatore Ruggieri, Steffen Staab
Encoding Scheme Categorical Feature Protected Attribute Fairness Implication Categorical Encoding

Fairness Implication

Papers

No Free Lunch: Retrieval-Augmented Generation Undermines Fairness in LLMs, Even for Vigilant Users

Strategic Demonstration Selection for Improved Fairness in LLM In-Context Learning

Long-Term Fairness Inquiries and Pursuits in Machine Learning: A Survey of Notions, Methods, and Challenges

FairTargetSim: An Interactive Simulator for Understanding and Explaining the Fairness Effects of Target Variable Definition

The Impact of Differential Feature Under-reporting on Algorithmic Fairness

On The Fairness Impacts of Hardware Selection in Machine Learning

Fairness Implications of Heterogeneous Treatment Effect Estimation with Machine Learning Methods in Policy-making

One Model Many Scores: Using Multiverse Analysis to Prevent Fairness Hacking and Evaluate the Influence of Model Design Decisions

On the Fairness Impacts of Private Ensembles Models

A Survey on Intersectional Fairness in Machine Learning: Notions, Mitigation, and Challenges

Mitigating Bias in Visual Transformers via Targeted Alignment

Algorithmic Fairness in Business Analytics: Directions for Research and Practice

Bias-inducing geometries: an exactly solvable data model with fairness implications

Evaluating the Fairness Impact of Differentially Private Synthetic Data

A Sandbox Tool to Bias(Stress)-Test Fairness Algorithms

Fairness Implications of Encoding Protected Categorical Attributes