Enhancing X-Resolution Integration through Federated Learning-based Building Learning Ecosystems

Abstract

The challenges of running federated learning (FL) in resource-constrained browser environments, such as limited GPU access and interruptions, are caused by tab closures or page refreshes. To address this, the FLEXIBLE learning ecosystem introduces a browser-based federated learning system that enables decentralized model training without sharing raw data, preserving user privacy and enhancing accessibility. Built on a microservices architecture with Kafka for asynchronous, fault-tolerant communication, the system allows users to participate without software installation. Experiments on a super-resolution task reveal performance disparities across devices—mid-range performance mobile laptops achieved complete zero-shot super-resolution (ZSSR) training-inference cycles under 3 seconds, while mobile devices took up to 13.78 seconds. Notably, image patching proved essential for enabling large-image processing in browsers, offering a key insight into optimizing FL in low-resource environments.