Achieving Fairness

Achieving fairness in machine learning focuses on mitigating biases that lead to discriminatory outcomes in AI systems, aiming for equitable treatment across different demographic groups. Current research explores various fairness metrics and techniques, including data pre-processing (e.g., reweighing, neutralization), algorithm modifications (e.g., adversarial perturbation, constrained optimization), and post-processing methods (e.g., leaf flipping in tree-based models), often applied within federated learning frameworks. This work is crucial for ensuring responsible AI development and deployment, impacting diverse fields like healthcare, criminal justice, and loan applications by promoting accountability and reducing societal inequalities.

Papers

November 13, 2024

Optimisation Strategies for Ensuring Fairness in Machine Learning: With and Without Demographics
Quan Zhou
Machine Learning Procedural Fairness Socio Demographic Achieving Fairness Bias Removal Machine Learning Fairness

October 26, 2024

Exploring Welfare Maximization and Fairness in Participatory Budgeting
Gogulapati Sreedurga
Procedural Fairness Fairness Notion Achieving Fairness Welfare Maximization Participatory Budgeting

October 21, 2024

Fair Bilevel Neural Network (FairBiNN): On Balancing fairness and accuracy via Stackelberg Equilibrium
Mehdi Yazdani-Jahromi, Ali Khodabandeh Yalabadi, AmirArsalan Rajabi, Aida Tayebi, Ivan Garibay, Ozlem Ozmen Garibay
Neural Network Bilevel Optimization Fairness Accuracy Fairness Aware Machine Achieving Fairness Fairness Objective Stackelberg Equilibrium Fairness Method

August 29, 2024

A Catalog of Fairness-Aware Practices in Machine Learning Engineering
Gianmario Voria, Giulia Sellitto, Carmine Ferrara, Francesco Abate, Andrea De Lucia, Filomena Ferrucci, Gemma Catolino, Fabio Palomba
Machine Learning Fairness Metric Fairness Aware Achieving Fairness

August 24, 2024

Ensuring Fairness with Transparent Auditing of Quantitative Bias in AI Systems
Chih-Cheng Rex Yuan, Bow-Yaw Wang
AI System AI Fairness Achieving Fairness Fairness Criterion

August 22, 2024

Unlocking Intrinsic Fairness in Stable Diffusion
Eunji Kim, Siwon Kim, Rahim Entezari, Sungroh Yoon
Procedural Fairness Text to Image Model Stable Diffusion Image Text Alignment Achieving Fairness

August 4, 2024

Rethinking Affect Analysis: A Protocol for Ensuring Fairness and Consistency
Guanyu Hu, Dimitrios Kollias, Eleni Papadopoulou, Paraskevi Tzouveli, Jie Wei, Xinyu Yang
Strong Consistency Expression Recognition Population Protocol Achieving Fairness Valence Arousal Estimation Action Unit Detection

July 29, 2024

AI-Driven Healthcare: A Survey on Ensuring Fairness and Mitigating Bias
Sribala Vidyadhari Chinta, Zichong Wang, Xingyu Zhang, Thang Doan Viet, Ayesha Kashif, Monique Antoinette Smith, Wenbin Zhang
Artificial Intelligence Timely Survey Procedural Fairness Medical AI Mitigating Bias Achieving Fairness Inclusive Artificial Intelligence

July 20, 2024

Implementing Fairness: the view from a FairDream
Thomas Souverain, Johnathan Nguyen, Nicolas Meric, Paul Égré
Best View AI Fairness Achieving Fairness Fairness Objective Equalized Odds Fairness Toolkits

June 24, 2024

Achieving Fairness Across Local and Global Models in Federated Learning
Disha Makhija, Xing Han, Joydeep Ghosh, Yejin Kim
Procedural Fairness Global Model Fairness Notion Achieving Fairness Proportional Fairness

May 15, 2024

The Unfairness of $\varepsilon$-Fairness
Tolulope Fadina, Thorsten Schmidt
Procedural Fairness Achieving Fairness Utility Based Probability Based Evaluation

May 14, 2024

Achieving Fairness Through Channel Pruning for Dermatological Disease Diagnosis
Qingpeng Kong, Ching-Hao Chiu, Dewen Zeng, Yu-Jen Chen, Tsung-Yi Ho, Jingtong hu, Yiyu Shi
Bias Mitigation Medical Image Classification Channel Pruning Achieving Fairness Dermatological Disease Diagnosis

March 19, 2024

FairSIN: Achieving Fairness in Graph Neural Networks through Sensitive Information Neutralization
Cheng Yang, Jixi Liu, Yunhe Yan, Chuan Shi
Graph Neural Network Graph Structured Data Fairness Metric Achieving Fairness GNN Backbone

December 26, 2023

Achieving Fairness in DareFightingICE Agents Evaluation Through a Delay Mechanism
Chollakorn Nimpattanavong, Thai Van Nguyen, Ibrahim Khan, Ruck Thawonmas, Worawat Choensawat, Kingkarn Sookhanaphibarn
Achieving Fairness Software Agent Excess Delay DareFightingICE Platform gRPC Latency

November 6, 2023

FinA: Fairness of Adverse Effects in Decision-Making of Human-Cyber-Physical-System
Tianyu Zhao, Salma Elmalaki
Procedural Fairness Decision Making Cyber Physical Achieving Fairness Side Effect Fair Credit

July 12, 2023

FAIRO: Fairness-aware Adaptation in Sequential-Decision Making for Human-in-the-Loop Systems
Tianyu Zhao, Mojtaba Taherisadr, Salma Elmalaki
Human in the Loop Achieving Fairness Fairness Utility Trade

June 1, 2023

Achieving Fairness in Multi-Agent Markov Decision Processes Using Reinforcement Learning
Peizhong Ju, Arnob Ghosh, Ness B. Shroff
Reinforcement Learning Markov Decision Process Multi Agent Policy Gradient Achieving Fairness Balancing Fairness

February 16, 2023

Towards Fair Machine Learning Software: Understanding and Addressing Model Bias Through Counterfactual Thinking
Zichong Wang, Yang Zhou, Meikang Qiu, Israat Haque, Laura Brown, Yi He, Jianwu Wang, David Lo, Wenbin Zhang
Machine Learning Human Understanding Model Bias Fairness Metric Fair Machine Learning Achieving Fairness Counterfactual Method

January 29, 2023

FedEBA+: Towards Fair and Effective Federated Learning via Entropy-Based Model
Lin Wang, Zhichao Wang, Sai Praneeth Karimireddy, Xiaoying Tang
Federated Learning Entropy Model Achieving Fairness FAIR Federated Learning Fairness Aware Aggregation

September 22, 2022

SCALES: From Fairness Principles to Constrained Decision-Making
Sreejith Balakrishnan, Jianxin Bi, Harold Soh
Procedural Fairness Achieving Fairness Ghanaian Musical Scale Equity Context