Fairness Learning

Fairness learning in machine learning aims to mitigate algorithmic bias, ensuring that models make equitable predictions across different demographic groups. Current research focuses on developing methods that address fairness across multiple sensitive attributes simultaneously, improve fairness generalization across diverse datasets and domains (including handling covariate and dependence shifts), and enhance fairness in specific applications like medical image analysis and deepfake detection. These efforts leverage techniques such as adversarial learning, data augmentation (including synthetic data generation), and novel loss functions to achieve improved fairness while maintaining accuracy, impacting the development of more equitable and trustworthy AI systems.

Papers

July 8, 2024

FairDiff: Fair Segmentation with Point-Image Diffusion
Wenyi Li, Haoran Xu, Guiyu Zhang, Huan-ang Gao, Mingju Gao, Mengyu Wang, Hao Zhao
Synthetic Image Guided Image Synthesis Fairness Learning

April 8, 2024

Flexible Fairness-Aware Learning via Inverse Conditional Permutation
Yuheng Lai, Leying Guan
Procedural Fairness Adversarial Learning Algorithmic Fairness Equalized Odds Permutation Importance Fairness Learning

February 27, 2024

Preserving Fairness Generalization in Deepfake Detection
Li Lin, Xinan He, Yan Ju, Xin Wang, Feng Ding, Shu Hu
Deepfake Detection Deep Fake Fairness Perception Fairness Learning Cross Domain Fraud Detection

November 27, 2023

FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understanding
Thanh-Dat Truong, Utsav Prabhu, Bhiksha Raj, Jackson Cothren, Khoa Luu
Contrastive Learning Continual LEArning Semantic Scene Continual Semantic Segmentation Feature Explanation Using Contrasting Concept Semantic Scene Segmentation Fairness Learning

November 23, 2023

Algorithmic Fairness Generalization under Covariate and Dependence Shifts Simultaneously
Chen Zhao, Kai Jiang, Xintao Wu, Haoliang Wang, Latifur Khan, Christan Grant, Feng Chen
Strong Generalization Covariate Shift Relevant Covariates Fairness Learning Dependence Shift

November 3, 2023

FairSeg: A Large-Scale Medical Image Segmentation Dataset for Fairness Learning Using Segment Anything Model with Fair Error-Bound Scaling
Yu Tian, Min Shi, Yan Luo, Ava Kouhana, Tobias Elze, Mengyu Wang
Segment Anything Model Segmentation Performance Fairness Datasets Fairness Learning Error Scaling

October 27, 2023

On the Fairness ROAD: Robust Optimization for Adversarial Debiasing
Vincent Grari, Thibault Laugel, Tatsunori Hashimoto, Sylvain Lamprier, Marcin Detyniecki
Robust Optimization Algorithmic Fairness Fairness Notion Adversarial Debiasing Fair Adversarial Fairness Learning Local Fairness

October 8, 2023

FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image Analysis
Raman Dutt, Ondrej Bohdal, Sotirios A. Tsaftaris, Timothy Hospedales
Procedural Fairness Parameter Efficient Fine Tuning Medical Image Analysis Generalization Gap Fairness Perception Fair Learning Fairness Learning

June 15, 2023

Harvard Glaucoma Fairness: A Retinal Nerve Disease Dataset for Fairness Learning and Fair Identity Normalization
Yan Luo, Yu Tian, Min Shi, Louis R. Pasquale, Lucy Q. Shen, Nazlee Zebardast, Tobias Elze, Mengyu Wang
Available Datasets Retinal Image Datasets Fairness Learning

May 25, 2023

Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environments
Thanh-Dat Truong, Hoang-Quan Nguyen, Bhiksha Raj, Khoa Luu
Continual LEArning Open World Semantic Scene COntinual Learning Framework Continual Semantic Segmentation Semantic Segmentation Problem Fairness Learning

October 19, 2022

On Learning Fairness and Accuracy on Multiple Subgroups
Changjian Shui, Gezheng Xu, Qi Chen, Jiaqi Li, Charles Ling, Tal Arbel, Boyu Wang, Christian Gagné
Bilevel Optimization Fair Predictor Fair Learning Fair Prediction Subgroup Description Fairness Learning

June 6, 2022

FIFA: Making Fairness More Generalizable in Classifiers Trained on Imbalanced Data
Zhun Deng, Jiayao Zhang, Linjun Zhang, Ting Ye, Yates Coley, Weijie J. Su, James Zou
Procedural Fairness Simple Classifier Imbalanced Data Fairness Aware Machine Fairness Learning Fairness Aware Training

Fairness Learning

Papers

FairDiff: Fair Segmentation with Point-Image Diffusion

Flexible Fairness-Aware Learning via Inverse Conditional Permutation

Preserving Fairness Generalization in Deepfake Detection

FALCON: Fairness Learning via Contrastive Attention Approach to Continual Semantic Scene Understanding

Algorithmic Fairness Generalization under Covariate and Dependence Shifts Simultaneously

FairSeg: A Large-Scale Medical Image Segmentation Dataset for Fairness Learning Using Segment Anything Model with Fair Error-Bound Scaling

On the Fairness ROAD: Robust Optimization for Adversarial Debiasing

FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image Analysis

Harvard Glaucoma Fairness: A Retinal Nerve Disease Dataset for Fairness Learning and Fair Identity Normalization

Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environments

On Learning Fairness and Accuracy on Multiple Subgroups

FIFA: Making Fairness More Generalizable in Classifiers Trained on Imbalanced Data