Plug In and Learn: Federated Intelligence over a Smart Grid of Models
This work addresses the problem of federated learning for researchers and practitioners by enabling coordination across heterogeneous models, though it appears incremental as it builds on existing regularized empirical risk minimization frameworks.
The authors tackled the challenge of coordinating diverse local models in federated learning by introducing a model-agnostic method that uses a graph-based regularizer to encourage similar predictions among connected models on shared unlabeled data, resulting in a flexible approach compatible with standard ML libraries.
We present a model-agnostic federated learning method that mirrors the operation of a smart power grid: diverse local models, like energy prosumers, train independently on their own data while exchanging lightweight signals to coordinate with statistically similar peers. This coordination is governed by a graph-based regularizer that encourages connected models to produce similar predictions on a shared, public unlabeled dataset. The resulting method is a flexible instance of regularized empirical risk minimization and supports a wide variety of local models - both parametric and non-parametric - provided they can be trained via regularized loss minimization. Such training is readily supported by standard ML libraries including scikit-learn, Keras, and PyTorch.