Presentation
SIGN IN TO VIEW THIS PRESENTATION Sign In
Enhancing Heterogeneous Federated Learning with Knowledge Extraction and Multi-Model Fusion
DescriptionConcerned with user data privacy, this paper presents a new federated learning (FL) method that trains machine learning models on edge devices without accessing sensitive data. Traditional FL methods, although privacy-protective, fail to manage model heterogeneity and incur high communication costs due to their reliance on aggregation methods. To address this limitation, we propose a resource-aware FL method that aggregates local knowledge from edge models and distills it into robust global knowledge through knowledge distillation. This method allows efficient multi-model knowledge fusion and the deployment of resource-aware models while preserving model heterogeneity. Our method improves communication cost and performance in heterogeneous data and models compared to existing FL algorithms. Notably, it reduces the communication cost of ResNet-32 by up to 50% and VGG-11 by up to 10x while delivering superior performance.
Event Type
Workshop
TimeMonday, 13 November 20234:45pm - 5pm MST
Location501-502
Artificial Intelligence/Machine Learning
W