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.
| Name | Size | |
|---|---|---|
|
cameraready.pdf
md5:a3ccdcfe8e5fa9089e424e51613d5098 |
244.7 kB | Download |
| All versions | This version | |
|---|---|---|
| Views | 207 | 207 |
| Downloads | 77 | 77 |
| Data volume | 18.8 MB | 18.8 MB |
| Unique views | 172 | 172 |
| Unique downloads | 72 | 72 |
- Publication date:
- February 4, 2021
- DOI:
-
- Published in:
- IEEE Communication Magazine:.
- Grants:
-
European Commission:
- Hexa-X - A flagship for B5G/6G vision and intelligent fabric of technology enablers connecting human, physical, and digital worlds (101015956)
- Communities:
- License (for files):
- Creative Commons Attribution 4.0 International