On In-network learning. A Comparative Study with Federated and Split Learning
This work addresses efficiency and performance challenges in distributed machine learning for wireless networks, presenting an incremental improvement over existing methods.
The paper tackles the problem of performing inference using distributively extracted features in wireless networks by proposing an in-network learning architecture, which achieves better accuracy and bandwidth savings compared to Federated and Split learning.
In this paper, we consider a problem in which distributively extracted features are used for performing inference in wireless networks. We elaborate on our proposed architecture, which we herein refer to as "in-network learning", provide a suitable loss function and discuss its optimization using neural networks. We compare its performance with both Federated- and Split learning; and show that this architecture offers both better accuracy and bandwidth savings.