InFL-UX: A Toolkit for Web-Based Interactive Federated Learning

2025-03-06

AI Summary

Traditional federated learning (FL) toolkits suffer from poor interactivity and impose high barriers for non-technical users, hindering broad participation. Method: This paper introduces the first browser-native FL toolkit designed for real-user interaction, built entirely on web-native technologies—WebAssembly, TensorFlow.js, WebRTC, and IndexedDB—and featuring a lightweight FL orchestration protocol. It enables zero-configuration, multi-device data upload, user-defined class labeling, and collaborative training of classification models directly in the browser. Contribution/Results: The work pioneers the deep integration of FL with interactive machine learning (IML), establishing a user-in-the-loop, decentralized, web-native FL paradigm. It bridges a critical gap at the intersection of FL and IML research and empirically validates—within real browser environments—the feasibility and usability of low-barrier, human-in-the-loop collaborative model training.

Technology Category

• Machine Learning: Distributed Machine Learning & Federated Learning
• Humans and AI: Human-in-the-loop Machine Learning
• Application Domains: Web

Application Category

• Responsible Web: Data and user privacy-enhancing technologies for the Web
• Systems and Infrastructure for Web, Mobile and WoT: Decentralized Web and Fediverse systems
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

This paper presents InFL-UX, an interactive, proof-of-concept browser-based Federated Learning (FL) toolkit designed to integrate user contributions seamlessly into the machine learning (ML) workflow. InFL-UX enables users across multiple devices to upload datasets, define classes, and collaboratively train classification models directly in the browser using modern web technologies. Unlike traditional FL toolkits, which often focus on backend simulations, InFL-UX provides a simple user interface for researchers to explore how users interact with and contribute to FL systems in real-world, interactive settings. By prioritising usability and decentralised model training, InFL-UX bridges the gap between FL and Interactive Machine Learning (IML), empowering non-technical users to actively participate in ML classification tasks.

Problem

• Enables collaborative ML model training in browsers.
• Bridges gap between Federated Learning and user interaction.
• Empowers non-technical users in classification tasks.

Innovation

• Browser-based Federated Learning toolkit
• Interactive user interface for FL
• Decentralized model training in browser