Model-Agnostic Federated Learning for Privacy-Preserving Systems
This study presents an innovative aggregation
scheme for model-agnostic, local, heterogeneous data models
within the domain of Federated Learning. The proposed ap-
proach imposes minimal constraints on local models, only ne-
cessitating local model parameters and distances from local data
centroids for a particular query. These requirements facilitate
the design of privacy-preserving learning systems. We intro-
duce a system architecture based on federated interpolation
to operationalize the proposed scheme. The accuracy of our
proposed scheme is evaluated using two distinct real-world
datasets. We compare our results to the extreme case of a
single-client scenario having complete access to all data points.
Our findings indicate that, on average, federated interpolation
maintains robust accuracy, experiencing a slight reduction of
less than 10% compared to the single-client model with full data
access.
Almohri, H. M. J., and Watson, L. T. “Model-Agnostic Federated Learning for Privacy-Preserving Systems.” IEEE Secure Development Conference (SecDev), Oct. 2023, pp. 99–105.