FLIS: Clustered Federated Learning Via Inference Similarity for Non-IID Data Distribution

FLIS: Clustered Federated Learning Via Inference Similarity for Non-IID Data Distribution

Conventional federated learning (FL) approaches are ineffective in scenarios where clients have significant differences in the distributions of their local data. The Non-IID data distribution in the client data causes a drift in the local model updates from the global optima, which significantly imp...

Full description

Bibliographic Details
Main Authors: Mahdi Morafah, Saeed Vahidian, Weijia Wang, Bill Lin
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Open Journal of the Computer Society
Subjects:
Clustering
data heterogeneity
federated learning
inference similarity
Non-IID data distribution
personalization
Online Access:https://ieeexplore.ieee.org/document/10081485/

Internet

https://ieeexplore.ieee.org/document/10081485/

Similar Items