Fairness Aware Training

Fairness-aware training aims to mitigate biases in machine learning models, ensuring equitable outcomes across different demographic groups. Current research focuses on developing algorithms and frameworks that integrate fairness considerations into the model training process itself (in-processing), encompassing techniques like re-weighting samples, adding fairness penalties to the loss function, and even co-optimizing data, algorithms, and neural network architectures. This work is crucial for addressing societal biases embedded in data and promoting the responsible development and deployment of AI systems across various applications, particularly in sensitive domains like healthcare and criminal justice. The ultimate goal is to improve both model accuracy and fairness simultaneously, a challenge actively pursued through both theoretical analysis and practical implementations.

Papers

October 3, 2024

Fair Decentralized Learning
Sayan Biswas, Anne-Marie Kermarrec, Rishi Sharma, Thibaud Trinca, Martijn de Vos
Machine Learning Model Decentralized Learning Cifar 10 Fairness Aware Training

July 18, 2024

Data-Algorithm-Architecture Co-Optimization for Fair Neural Networks on Skin Lesion Dataset
Yi Sheng, Junhuan Yang, Jinyang Li, James Alaina, Xiaowei Xu, Yiyu Shi, Jingtong Hu, Weiwen Jiang, Lei Yang
Neural Network Neural Network Architecture Skin Lesion Co Design Medical AI Contextual Biasing Medical Artificial Intelligence Fairness Aware Training

May 9, 2024

Aequitas Flow: Streamlining Fair ML Experimentation
Sérgio Jesus, Pedro Saleiro, Inês Oliveira e Silva, Beatriz M. Jorge, Rita P. Ribeiro, João Gama, Pedro Bizarro, Rayid Ghani
Fair Machine Learning Fairness Aware Training

November 10, 2023

Fair Supervised Learning with A Simple Random Sampler of Sensitive Attributes
Jinwon Sohn, Qifan Song, Guang Lin
Fair Machine Learning Sensitive Attribute Fairness Aware Machine Random Sampling Fairness Aware Training

May 17, 2023

Mitigating Group Bias in Federated Learning: Beyond Local Fairness
Ganghua Wang, Ali Payani, Myungjin Lee, Ramana Kompella
Group Fairness Model Fairness Mitigating Bias Fairness Aware Training Local Fairness Fair Training

March 1, 2023

Re-weighting Based Group Fairness Regularization via Classwise Robust Optimization
Sangwon Jung, Taeeon Park, Sanghyuk Chun, Taesup Moon
Robust Optimization Group Fairness Fairness Metric Fairness Accuracy Fairness Regularization Fairness Aware Training Group Fairness Metric

June 29, 2022

Fairness via In-Processing in the Over-parameterized Regime: A Cautionary Tale
Akshaj Kumar Veldanda, Ivan Brugere, Jiahao Chen, Sanghamitra Dutta, Alan Mishler, Siddharth Garg
Neural Network Procedural Fairness Complex Process Model Fairness Efficient Optimization Cautionary TALE Parameterized Regime Fairness Aware Training

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

April 6, 2022

FairNeuron: Improving Deep Neural Network Fairness with Adversary Games on Selective Neurons
Xuanqi Gao, Juan Zhai, Shiqing Ma, Chao Shen, Yufei Chen, Qian Wang
Neural Network Model Fairness Fairness Accuracy Adversarial Game Fairness Aware Training Selective Neuron