Publikation
FedAvgen: Metadata for Model Aggregation In Communication Systems
Anthony Kiggundu; Dennis Krummacker; Hans D. Schotten
In: 11th IEEE NetSoft 2025 Proceedings. Open Source 6G Networks for Connecting the Unconnected Workshop (Open6GNet-2025), IEEE NetSoft 2025, June 23, Budapest, Hungary, IEEE, 6/2025.
Zusammenfassung
To improve business efficiency and minimize costs,
Artificial Intelligence (AI) practitioners have adopted a shift from
formulating models from scratch towards sharing pretrained
models. The pretrained models are then aggregated into a
global model with higher generalization capabilities, which is
afterwards distributed to the client devices. This approach is
known as federated learning and inherently utilizes different
techniques to select the candidate client models averaged to
obtain the global model. However, in the case of communication
systems, the approach grapples with challenges arising from
the existential diversity in device profiles. The multiplicity in
profiles motivates our conceptual assessment of a metaheuristic
algorithm (FedAvgen), which relates each pretrained model with
its weight space as metadata, to a phenotype and genotype,
respectively. This parent-child genetic evolution characterizes the
global averaging step in federated learning. We then compare
the results of our approach to two widely adopted baseline
federated learning algorithms like Federated Averaging (FedAvg)
and Federated Stochastic Gradient Descent (FedSGD).