Clustered Graph Federated Personalized Learning

This paper proposes a graph federated learning approach wherein multiple servers collaborate to enhance personalized learning over clustered clients, essentially performing correlated learning tasks. In contrast to earlier approaches, relying on a cluster-dedicated server topology, the proposed grap...

Full description

Saved in:
Bibliographic Details
Main Authors: Gauthier, Francois, Gogineni, Vinay Chakravarthi, Werner, Stefan, Huang, Yih-Fang, Kuh, Anthony
Format: Conference Proceeding
Language:English
Subjects:
Convex functions
Data models
Federated learning
graph federated learning
inter-cluster learning
multi-server architecture
Numerical models
Numerical simulation
Personalized federated learning
Processor scheduling
Topology
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper proposes a graph federated learning approach wherein multiple servers collaborate to enhance personalized learning over clustered clients, essentially performing correlated learning tasks. In contrast to earlier approaches, relying on a cluster-dedicated server topology, the proposed graph federated multitask learning (GFedMt) framework adopts a more general setting wherein clients of the same cluster are distributed across servers. In order to address problems with unbalanced client distributions among servers and clusters as well as data shortage of isolated clients, servers perform intra-cluster and inter-cluster learning collaboratively through local interaction with neighboring servers. Clients use the alternating direction method of multipliers (ADMM) to learn their local models. Numerical simulations demonstrate the ability of the proposed method to ensure fast and accurate convergence when data is scarce.
ISSN:2576-2303
DOI:10.1109/IEEECONF56349.2022.10051979