Skip to content
conftrace_
2024 AAAI AAAI 2024

Adapted Weighted Aggregation in Federated Learning

Abstract

Abstract This study introduces FedAW, a novel federated learning algorithm that uses a weighted aggregation mechanism sensitive to the quality of client datasets, leading to better model performance and faster convergence on diverse datasets, validated using Colored MNIST.

Authors

Yitong Tang

Topics

Artificial Intelligence > Learning Paradigms > Federated Learning Machine Learning > Optimization & Theory > Optimization Machine Learning > Learning Paradigms > Federated Learning

Keywords

federated learning distributed learning model convergence client selection weighted aggregation client dataset quality
Download PDF

More from AAAI 2024

All AAAI 2024 papers →
Defog Artificial Intelligence Glasses: Neural Networks for the Imperfect Real World
Multi-world Model in Continual Reinforcement Learning
AI-Enhanced Art Appreciation: Generating Text from Artwork to Promote Inclusivity
Deep Learning for Style Transfer and Experimentation with Audio Effects and Music Creation
Validation, Robustness, and Accuracy of Perturbation-Based Sensitivity Analysis Methods for Time-Series Deep Learning Models
SemLa: A Visual Analysis System for Fine-Grained Text Classification