Plug In and Learn: Federated Intelligence over a Smart Grid of Models

TL;DR

This paper introduces a flexible federated learning approach inspired by smart grids, enabling diverse local models to coordinate via lightweight signals using graph-based regularization, compatible with standard ML libraries.

Contribution

It proposes a model-agnostic federated learning method that supports various local models and uses graph-based regularization for coordination, mirroring smart grid operations.

Findings

Supports a wide variety of local models including parametric and non-parametric

Uses graph-based regularizer for model coordination

Compatible with standard ML libraries like scikit-learn, Keras, and PyTorch

Abstract

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.