Fairness Aware Aggregation

Fairness-aware aggregation in machine learning focuses on developing methods to combine predictions or model updates from multiple sources while mitigating biases and ensuring equitable outcomes across different groups or clients. Current research emphasizes techniques like weighted averaging based on client performance or staleness of updates, using synthetic data to protect privacy while promoting fairness, and employing online convex optimization frameworks to adapt aggregation strategies dynamically. These advancements are crucial for addressing fairness concerns in federated learning and other distributed settings, improving the reliability and societal impact of machine learning models.

Papers

September 14, 2024

Using Synthetic Data to Mitigate Unfairness and Preserve Privacy through Single-Shot Federated Learning
Chia-Yuan Wu, Frank E. Curtis, Daniel P. Robinson
Synthetic Data Privacy Policy Fairness Metric Weight Aggregation Fairness Aware Aggregation

June 5, 2024

FedStaleWeight: Buffered Asynchronous Federated Learning with Fair Aggregation via Staleness Reweighting
Jeffrey Ma, Alan Tu, Yiling Chen, Vijay Janapa Reddi
Convergence Guarantee Asynchronous Federated Learning Fairness Aware Aggregation Staleness Problem

May 31, 2024

Pursuing Overall Welfare in Federated Learning through Sequential Decision Making
Seok-Ju Hahn, Gi-Soo Kim, Junghye Lee
Federated Learning Online Convex Optimization Sequential Decision Making Robust Aggregation Social Welfare Fairness Aware Aggregation Seller Side Outcome Fairness

May 9, 2024

Truthful Aggregation of LLMs with an Application to Online Advertising
Ermis Soumalias, Michael J. Curry, Sven Seuken
Large Language Model Application Proficiency LLM Response Online Advertising Self Interested Agent Auction Mechanism Fairness Aware Aggregation

November 25, 2023

Robust Graph Neural Networks via Unbiased Aggregation
Zhichao Hou, Ruiqi Feng, Tyler Derr, Xiaorui Liu
Graph Neural Network Adversarial Robustness Robust Graph Neural Network Fairness Aware Aggregation

June 26, 2023

Proportional Aggregation of Preferences for Sequential Decision Making
Nikhil Chandak, Shashwat Goel, Dominik Peters
Preference Feedback Sequential Decision Making Voting Rule Multiwinner Voting Approval Voting Fairness Aware Aggregation Proportional Representation

January 29, 2023

FedEBA+: Towards Fair and Effective Federated Learning via Entropy-Based Model
Lin Wang, Zhichao Wang, Sai Praneeth Karimireddy, Xiaoying Tang
Federated Learning Entropy Model Achieving Fairness FAIR Federated Learning Fairness Aware Aggregation

November 29, 2022

Isolation and Impartial Aggregation: A Paradigm of Incremental Learning without Interference
Yabin Wang, Zhiheng Ma, Zhiwu Huang, Yaowei Wang, Zhou Su, Xiaopeng Hong
Incremental Learning Two Stage Catastrophic Interference Hui Walter Paradigm Social Isolation Incremental Learning Framework Training Bottleneck Fairness Aware Aggregation

September 27, 2022

FAIR-FATE: Fair Federated Learning with Momentum
Teresa Salazar, Miguel Fernandes, Helder Araujo, Pedro Henriques Abreu
Residual Momentum Fairness Aware Machine FAIR Federated Learning Fairness Aware Aggregation Fair Federated Learning

April 6, 2022

Consensual Aggregation on Random Projected High-dimensional Features for Regression
Sothea Has
Novel Regression Cross Validation Random Projection High Dimensional Feature Robust Aggregation Fairness Aware Aggregation

Fairness Aware Aggregation

Papers

Using Synthetic Data to Mitigate Unfairness and Preserve Privacy through Single-Shot Federated Learning

FedStaleWeight: Buffered Asynchronous Federated Learning with Fair Aggregation via Staleness Reweighting

Pursuing Overall Welfare in Federated Learning through Sequential Decision Making

Truthful Aggregation of LLMs with an Application to Online Advertising

Robust Graph Neural Networks via Unbiased Aggregation

Proportional Aggregation of Preferences for Sequential Decision Making

FedEBA+: Towards Fair and Effective Federated Learning via Entropy-Based Model

Isolation and Impartial Aggregation: A Paradigm of Incremental Learning without Interference

FAIR-FATE: Fair Federated Learning with Momentum

Consensual Aggregation on Random Projected High-dimensional Features for Regression