Federated Learning Playground

2026-02-22

AI Summary

Federated learning presents significant entry barriers due to challenges such as non-IID data distributions, local overfitting, and scalability. To address these issues, this work proposes the first browser-based interactive educational platform that enables users to experiment with diverse client data distributions, model hyperparameters, and aggregation algorithms—without writing code or requiring any setup—within a zero-configuration sandbox environment. The platform uniquely integrates real-time visualizations to illustrate the immediate effects of these choices on both local and global models. By introducing interactive visualization into federated learning education for the first time, it facilitates rapid prototyping and comparative analysis of methods, substantially lowering the conceptual and practical barriers to understanding and accelerating the broader adoption and application of distributed AI.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Search and Optimization: Distributed Search
• Computer Vision: Large Vision Models

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

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.

Problem

• Federated Learning
• non-IID data
• local overfitting
• scalability
• educational tool

Innovation

• Federated Learning
• Interactive Visualization
• Non-IID Data
• Browser-based Platform
• Educational Tool