Substantive Equality

Substantive equality focuses on achieving equitable outcomes, not just equal treatment, particularly in the context of algorithmic systems and machine learning. Current research emphasizes developing methods to mitigate bias in algorithms, ensuring fairness in algorithmic recourse (providing actionable recommendations to individuals affected by algorithmic decisions), and measuring equality of opportunity across different demographic groups, often using novel metrics and model architectures like Bayesian-Theory based Bias Removal and Binned Fair Quantile Regression. This work is crucial for building trustworthy and fair AI systems, addressing societal inequalities amplified by algorithmic bias and promoting more just and equitable outcomes in various applications.

Papers

October 11, 2024

Public Transport Network Design for Equality of Accessibility via Message Passing Neural Networks and Reinforcement Learning
Duo Wang, Maximilien Chau, Andrea Araldo
Reinforcement Learning Metaheuristic Algorithm Message Passing Neural Network Public Transit Accessibility Issue Substantive Equality Transit Network Design Overlay Network

August 20, 2024

Promoting Equality in Large Language Models: Identifying and Mitigating the Implicit Bias based on Bayesian Theory
Yongxin Deng, Xihe Qiu, Xiaoyu Tan, Jing Pan, Chen Jue, Zhijun Fang, Yinghui Xu, Wei Chu, Yuan Qi
Large Language Model Implicit Bias Biased Datasets Biased Behavior Bias Removal Substantive Equality

January 29, 2024

Fairness in Algorithmic Recourse Through the Lens of Substantive Equality of Opportunity
Andrew Bell, Joao Fonseca, Carlo Abrate, Francesco Bonchi, Julia Stoyanovich
Artificial Intelligence Procedural Fairness Emerging Opportunity Camera Lens Algorithmic Recourse Normative System Substantive Equality

November 3, 2023

Equal Opportunity of Coverage in Fair Regression
Fangxin Wang, Lu Cheng, Ruocheng Guo, Kay Liu, Philip S. Yu
Predictive Uncertainty Fair Machine Learning Higher Coverage Rate Substantive Equality Fair Regression Uncertainty Aware Fairness

June 8, 2023

An adaptive augmented Lagrangian method for training physics and equality constrained artificial neural networks
Shamsulhaq Basir, Inanc Senocak
Neural Network Constrained Optimization Theoretical Physic Navier Stokes LLM Adaptation Lagrangian Method Substantive Equality Incompressible Fluid

May 8, 2023

Accelerated Algorithms for a Class of Optimization Problems with Equality and Box Constraints
Anjali Parashar, Priyank Srivastava, Anuradha M. Annaswamy
Optimization Problem Convex Optimization True Class Accelerated Convergence Accelerated Algorithm Substantive Equality Box Constraint

February 17, 2023

Measuring Equality in Machine Learning Security Defenses: A Case Study in Speech Recognition
Luke E. Richards, Edward Raff, Cynthia Matuszek
Machine Learning Case Study Speech Recognition Adversarial Robustness Based Rejection Active Defense Substantive Equality

November 21, 2022

Equality of Effort via Algorithmic Recourse
Francesca E. D. Raimondi, Andrew R. Lawrence, Hana Chockler
Practical Algorithm Procedural Fairness Algorithmic Recourse Manual Effort Substantive Equality

July 7, 2022

Group Equality in Adaptive Submodular Maximization
Shaojie Tang, Jing Yuan
Submodular Maximization Substantive Equality Adaptive Submodular

July 6, 2022

Towards Substantive Conceptions of Algorithmic Fairness: Normative Guidance from Equal Opportunity Doctrines
Falaah Arif Khan, Eleni Manis, Julia Stoyanovich
Algorithmic Fairness Normative Reasoning Egalitarian Fairness Substantive Equality

Substantive Equality

Papers

Public Transport Network Design for Equality of Accessibility via Message Passing Neural Networks and Reinforcement Learning

Promoting Equality in Large Language Models: Identifying and Mitigating the Implicit Bias based on Bayesian Theory

Fairness in Algorithmic Recourse Through the Lens of Substantive Equality of Opportunity

Equal Opportunity of Coverage in Fair Regression

An adaptive augmented Lagrangian method for training physics and equality constrained artificial neural networks

Accelerated Algorithms for a Class of Optimization Problems with Equality and Box Constraints

Measuring Equality in Machine Learning Security Defenses: A Case Study in Speech Recognition

Equality of Effort via Algorithmic Recourse

Group Equality in Adaptive Submodular Maximization

Towards Substantive Conceptions of Algorithmic Fairness: Normative Guidance from Equal Opportunity Doctrines