We present a model-agnostic federated learning method for decentralized data with an intrinsic network structure. The network structure reflects similarities between the (statistics of) local datasets and, in turn, their associated local models. Our method is an instance of empirical risk minimization, using a regularization term that is constructed from the network structure of data. In particular, we require well-connected local models, forming clusters, to yield similar predictions on a common test set. In principle our method can be applied to any collection of local models. The only restriction put on these local models is that they allow for efficient implementation of regularized empirical risk minimization (training). Such implementations might be available in the form of high-level programming frameworks such as \texttt{scikit-learn}, \texttt{Keras} or \texttt{PyTorch}.
Original languageEnglish
Publication statusAccepted/In press - 1 Feb 2023
MoE publication typeB1 Journal article


  • Computer Science - Machine Learning


Dive into the research topics of 'Towards Model-Agnostic Federated Learning over Networks'. Together they form a unique fingerprint.

Cite this