Journal article Open Access

Federated Learning at the Network Edge: When Not All Nodes are Created Equal

Francesco Malandrino; Carla Fabiana Chiasserini

Under the federated learning paradigm, a set of nodes can cooperatively train a machine learning model with the help of a centralized server. Such a server is also tasked with assigning a weight to the information received from each node, and often also to drop too-slow nodes from the learning process. Both decisions have major impact on the resulting learning performance, and can interfere with each other in counter-intuitive ways. In this paper, we focus on edge networking scenarios and investigate existing and novel approaches to such model-weighting and node-dropping decisions. Leveraging a set of real- world experiments, we find that popular, straightforward decision-making approaches may yield poor performance, and that considering the quality of data in addition to its quantity can substantially improve learning.

Files (244.7 kB)
Name Size
cameraready.pdf
md5:a3ccdcfe8e5fa9089e424e51613d5098
244.7 kB Download
207
77
views
downloads
All versions This version
Views 207207
Downloads 7777
Data volume 18.8 MB18.8 MB
Unique views 172172
Unique downloads 7272

Share

Cite as