Rethinking Fairness

Rethinking fairness in artificial intelligence focuses on mitigating biases in algorithms and ensuring equitable outcomes across diverse populations. Current research emphasizes developing and applying fairness metrics, exploring techniques like model stitching and federated learning to improve fairness in various model architectures, and investigating the interplay between fairness, privacy, and human-AI collaboration. This work is crucial for building trustworthy AI systems and addressing societal concerns about algorithmic discrimination, impacting both the development of ethical AI guidelines and the deployment of AI in high-stakes applications.

Papers

September 17, 2024

Challenging Fairness: A Comprehensive Exploration of Bias in LLM-Based Recommendations
Shahnewaz Karim Sakib, Anindya Bijoy Das
Large Language Model Language Model Absolute Stance Bias Movie Recommendation Recommendation Quality Depth Analysis Rethinking Fairness

July 16, 2024

EARN Fairness: Explaining, Asking, Reviewing and Negotiating Artificial Intelligence Fairness Metrics Among Stakeholders
Lin Luo, Yuri Nakao, Mathieu Chollet, Hiroya Inakoshi, Simone Stumpf
Fairness Metric AI Fairness Different Stakeholder Text Review Rethinking Fairness

January 29, 2024

FedFair^3: Unlocking Threefold Fairness in Federated Learning
Simin Javaherian, Sanjeev Panta, Shelby Williams, Md Sirajul Islam, Li Chen
Fairness Accuracy Rethinking Fairness

January 16, 2024

Achieve Fairness without Demographics for Dermatological Disease Diagnosis
Ching-Hao Chiu, Yu-Jen Chen, Yawen Wu, Yiyu Shi, Tsung-Yi Ho
Bias Mitigation Sensitive Attribute Socio Demographic Dermatological Disease Diagnosis Rethinking Fairness Dermatological Disease Datasets

November 6, 2023

The Fairness Stitch: Unveiling the Potential of Model Stitching in Neural Network De-Biasing
Modar Sulaiman, Kallol Roy
Deep Learning Model Procedural Fairness Full Potential Fairness Constraint Debiasing Framework Bias Challenge Rethinking Fairness Model Stitching

October 5, 2023

Rethinking Fairness for Human-AI Collaboration
Haosen Ge, Hamsa Bastani, Osbert Bastani
Human Ai Collaboration Algorithmic Fairness Algorithmic Decision Fair Algorithm Recommendation Fairness Rethinking Fairness

June 25, 2023

Privacy and Fairness in Federated Learning: on the Perspective of Trade-off
Huiqiang Chen, Tianqing Zhu, Tao Zhang, Wanlei Zhou, Philip S. Yu
Procedural Fairness Visual Perspective Privacy Policy Fairness Issue Rethinking Fairness

March 15, 2023

Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoML
Hilde Weerts, Florian Pfisterer, Matthias Feurer, Katharina Eggensperger, Edward Bergman, Noor Awad, Joaquin Vanschoren, Mykola Pechenizkiy, Bernd Bischl, Frank Hutter
Machine Learning Procedural Fairness Emerging Opportunity Fair Machine Learning State Aware Guideline Fairness Research Fair Credit Rethinking Fairness

February 9, 2023

Designing Fairness in Autonomous Peer-to-peer Energy Trading
Varsha Behrunani, Andrew Irvine, Giuseppe Belgioioso, Philipp Heer, John Lygeros, Florian Dörfler
Peer to Peer Energy Trading Rethinking Fairness Peer to Peer Trading

December 16, 2022

Provable Fairness for Neural Network Models using Formal Verification
Giorgian Borca-Tasciuc, Xingzhi Guo, Stanley Bak, Steven Skiena
Machine Learning Model Procedural Fairness Neural Network Model Formal Verification Formal Proof Rethinking Fairness

May 6, 2022

Rethinking Fairness: An Interdisciplinary Survey of Critiques of Hegemonic ML Fairness Approaches
Lindsay Weinberg
AI Fairness Interdisciplinary Perspective Fairness Intervention Lower Critique Accuracy ML Fairness Rethinking Fairness

December 10, 2021

Assessing the Fairness of AI Systems: AI Practitioners' Processes, Challenges, and Needs for Support
Michael Madaio, Lisa Egede, Hariharan Subramonyam, Jennifer Wortman Vaughan, Hanna Wallach
Technical Challenge Procedural Fairness AI System Customer Service AI Practitioner Fair Credit Performance Disparity Rethinking Fairness

Rethinking Fairness

Papers

Challenging Fairness: A Comprehensive Exploration of Bias in LLM-Based Recommendations

EARN Fairness: Explaining, Asking, Reviewing and Negotiating Artificial Intelligence Fairness Metrics Among Stakeholders

FedFair^3: Unlocking Threefold Fairness in Federated Learning

Achieve Fairness without Demographics for Dermatological Disease Diagnosis

The Fairness Stitch: Unveiling the Potential of Model Stitching in Neural Network De-Biasing

Rethinking Fairness for Human-AI Collaboration

Privacy and Fairness in Federated Learning: on the Perspective of Trade-off

Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoML

Designing Fairness in Autonomous Peer-to-peer Energy Trading

Provable Fairness for Neural Network Models using Formal Verification

Rethinking Fairness: An Interdisciplinary Survey of Critiques of Hegemonic ML Fairness Approaches

Assessing the Fairness of AI Systems: AI Practitioners' Processes, Challenges, and Needs for Support