TraceFL: Interpretability-Driven Debugging in Federated Learning via Neuron Provenance

In Federated Learning, clients train models on local data and send updates to a central server, which aggregates them into a global model using a fusion algorithm. This collaborative yet privacy-preserving training comes at a cost. FL developers face significant challenges in attributing global mode...

Full description

Bibliographic Details

Published in:	Proceedings / International Conference on Software Engineering pp. 2264 - 2276
Main Authors:	Gill, Waris, Anwar, Ali, Gulzar, Muhammad Ali
Format:	Conference Proceeding
Language:	English
Published:	IEEE 26.04.2025
Subjects:	Accuracy Data models Debugging Explainability Federated learning Interpretability Location awareness Machine Learning Neurons Predictive models Text categorization Training Transformer Transformers
ISSN:	1558-1225
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!