SPATL-XLC: An Explainability-Driven Framework for Efficient and Robust Federated Learning Under Non-IID Data

SPATL-XLC: An Explainability-Driven Framework for Efficient and Robust Federated Learning Under Non-IID Data

Federated learning (FL) enables multiple devices to collectively train a machine learning model without sharing private data. However, when data across devices differ significantly (non-IID),training becomes less accurate and difficult to understand in terms of how the model makes decisions (explain...

Full description

Saved in:
Bibliographic Details
Main Authors: Samuel Hailemariam Seifu, Beakal Gizachew Assefa
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Federated learning
non-IID data
explainable AI (XAI)
SHAP
client clustering
model pruning
Online Access:https://ieeexplore.ieee.org/document/11082156/
Tags: Add Tag
No Tags, Be the first to tag this record!
Login for hold and recall information

Internet

https://ieeexplore.ieee.org/document/11082156/

Similar Items