Fair Training

Fair training in machine learning aims to mitigate biases that lead to unfair outcomes for different demographic groups or tasks. Current research focuses on developing algorithms and techniques to achieve fairness across various settings, including federated learning and graph convolutional networks, often employing methods like dynamic resource allocation, regularization, and pre-processing to adjust for data imbalances or correlation shifts. These advancements are crucial for building trustworthy and equitable AI systems, impacting both the theoretical understanding of fairness and the development of fairer applications across diverse domains.

Papers

April 22, 2024

Fair Concurrent Training of Multiple Models in Federated Learning
Marie Siew, Haoran Zhang, Jong-Ik Park, Yuezhou Liu, Yichen Ruan, Lili Su, Stratis Ioannidis, Edmund Yeh, Carlee Joe-Wong
Federated Learning Multiple Model Fairness Aware Learning Fair Training

February 29, 2024

To Pool or Not To Pool: Analyzing the Regularizing Effects of Group-Fair Training on Shared Models
Cyrus Cousins, I. Elizabeth Kumar, Suresh Venkatasubramanian
Fair Machine Learning Fairness Aware Machine Regularization Effect Rademacher Complexity Tight Bound Fair Learning Shared Model Fair Training

January 26, 2024

FairSample: Training Fair and Accurate Graph Convolutional Neural Networks Efficiently
Zicun Cong, Shi Baoxu, Shan Li, Jaewon Yang, Qi He, Jian Pei
Model Fairness Graph Convolutional Neural Network Fairness Property Unbiased Segmentation Fair 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

May 4, 2023

Training Is Everything: Artificial Intelligence, Copyright, and Fair Training
Andrew W. Torrance, Bill Tomlinson
Artificial Intelligence Training Data Copyright Protection Intellectual Property Neural Engine Fair Use Fair Training

April 4, 2023

Exploration of Lightweight Single Image Denoising with Transformers and Truly Fair Training
Haram Choi, Cheolwoong Na, Jinseop Kim, Jihoon Yang
Transformer Megatron Decepticons Environment Exploration Image Denoising Lightweight Transformer Baseline Transformer Single Image Denoising Fair Training

February 5, 2023

Improving Fair Training under Correlation Shifts
Yuji Roh, Kangwook Lee, Steven Euijong Whang, Changho Suh
Group Fairness Model Fairness Fair Algorithm Fairness Mitigation Correlation Shift Fair Training