Fairness Loss

Fairness loss in machine learning focuses on modifying model training to mitigate biases and ensure equitable outcomes across different demographic groups or individuals. Current research explores various fairness-aware loss functions integrated into diverse model architectures, including neural networks (CNNs, GNNs), decision trees, and recommender systems, often addressing challenges like bias transfer in multi-task learning and online settings. This research is crucial for developing trustworthy and ethical AI systems, impacting fields ranging from healthcare and criminal justice to online services, where biased predictions can have significant societal consequences. The goal is to achieve a balance between model accuracy and fairness, often measured using metrics like demographic parity or equalized odds.

Papers

October 20, 2023

FairBranch: Mitigating Bias Transfer in Fair Multi-task Learning
Arjun Roy, Christos Koutlis, Symeon Papadopoulos, Eirini Ntoutsi
Multi Task Learning Fairness Loss Sentiment Transfer Task Grouping

October 17, 2023

Enhancing Group Fairness in Online Settings Using Oblique Decision Forests
Somnath Basu Roy Chowdhury, Nicholas Monath, Ahmad Beirami, Rahul Kidambi, Avinava Dubey, Amr Ahmed, Snigdha Chaturvedi
Group Fairness Fairness Loss Oblique Decision Tree

September 4, 2023

In-processing User Constrained Dominant Sets for User-Oriented Fairness in Recommender Systems
Zhongxuan Han, Chaochao Chen, Xiaolin Zheng, Weiming Liu, Jun Wang, Wenjie Cheng, Yuyuan Li
Recommender System Recommendation Performance Fairness Loss User Oriented Fairness

August 29, 2023

Ensuring User-side Fairness in Dynamic Recommender Systems
Hyunsik Yoo, Zhichen Zeng, Jian Kang, Ruizhong Qiu, David Zhou, Zhining Liu, Fei Wang, Charlie Xu, Eunice Chan, Hanghang Tong
Group Fairness Recommendation Fairness Fairness Loss Dynamic Recommender System User Oriented Fairness

July 3, 2023

Unbiased Pain Assessment through Wearables and EHR Data: Multi-attribute Fairness Loss-based CNN Approach
Sharmin Sultana, Md Mahmudur Rahman, Atqiya Munawara Mahi, Shao-Hsien Liu, Mohammad Arif Ul Alam
Artificial Intelligence Convolutional Neural Network Wearable Device Patient Data Fairness Assessment Fairness Loss Pain Assessment

June 27, 2023

FAIRER: Fairness as Decision Rationale Alignment
Tianlin Li, Qing Guo, Aishan Liu, Mengnan Du, Zhiming Li, Yang Liu
Deep Neural Network Procedural Fairness Rationale Alignment Fairness Regularization Fairness Loss Fair Prediction Neuron Alignment

May 22, 2023

Transferring Fairness using Multi-Task Learning with Limited Demographic Information
Carlos Aguirre, Mark Dredze
Multi Task Learning Fairness Loss Intersectional Fairness Demographic Fairness

May 18, 2023

RobustFair: Adversarial Evaluation through Fairness Confusion Directed Gradient Search
Xuran Li, Peng Wu, Kaixiang Dong, Zhen Zhang, Yanting Chen
Native Robustness Adversarial Example Adversarial Perturbation Adversarial Evaluation Adversarial Instance Fairness Loss

April 7, 2023

Fairness through Aleatoric Uncertainty
Anique Tahir, Lu Cheng, Huan Liu
Procedural Fairness Fair Machine Learning Aleatoric Uncertainty Fairness Loss Fairness Utility Trade

November 18, 2022

July 7, 2022

Enhancing Fairness of Visual Attribute Predictors
Tobias Hänel, Nishant Kumar, Dmitrij Schlesinger, Mengze Li, Erdem Ünal, Abouzar Eslami, Stefan Gumhold
Bias Mitigation Model Fairness Fairness Regularization Fairness Loss

June 15, 2022

Disparate Impact in Differential Privacy from Gradient Misalignment
Maria S. Esipova, Atiyeh Ashari Ghomi, Yaqiao Luo, Jesse C. Cresswell
Differential Privacy Private Stochastic Gradient Descent Gradient Alignment Private Model Training Disparate Impact Fairness Loss

May 20, 2022

CertiFair: A Framework for Certified Global Fairness of Neural Networks
Haitham Khedr, Yasser Shoukry
Neural Network New Framework Fairness Loss Fairness Property Fairness Datasets

January 10, 2022

FairEdit: Preserving Fairness in Graph Neural Networks through Greedy Graph Editing
Donald Loveland, Jiayi Pan, Aaresh Farrokh Bhathena, Yiyang Lu
Graph Neural Network Procedural Fairness Manipulation Edge Detection Module Fairness Loss Graph Edit Distance GNN Method Fair Inference

November 5, 2021

Increasing Fairness in Predictions Using Bias Parity Score Based Loss Function Regularization
Bhanu Jain, Manfred Huber, Ramez Elmasri
Loss Function Human Prediction Procedural Fairness Bias Score Fairness Loss Recidivism Model