Federated Learning Playground

TL;DR

Federated Learning Playground is an interactive browser-based tool that helps users understand core federated learning concepts through real-time visualizations and experimentation with various data distributions, hyperparameters, and algorithms.

Contribution

It introduces an accessible, visual platform for learning and prototyping federated learning methods without coding, enhancing education and research in the field.

Findings

Enables exploration of non-IID data effects

Demonstrates impact of hyperparameters on model convergence

Facilitates comparison of aggregation algorithms

Abstract

We present Federated Learning Playground, an interactive browser-based platform inspired by and extends TensorFlow Playground that teaches core Federated Learning (FL) concepts. Users can experiment with heterogeneous client data distributions, model hyperparameters, and aggregation algorithms directly in the browser without coding or system setup, and observe their effects on client and global models through real-time visualizations, gaining intuition for challenges such as non-IID data, local overfitting, and scalability. The playground serves as an easy to use educational tool, lowering the entry barrier for newcomers to distributed AI while also offering a sandbox for rapidly prototyping and comparing FL methods. By democratizing exploration of FL, it promotes broader understanding and adoption of this important paradigm.