United Intelligence: Federated Learning for the Future of Technology
Year: 2024
Type: article
Abstract: Federated Learning (FL) is rapidly transforming how we approach machine learning by offering a decentralized, privacy-first way to train models. Instead of sending data to a central server, FL enables devices to collaborate and learn without ever sharing sensitive information, making it a game-changer for privacy-conscious applications. In this study, we dive deep into three leading FL frameworks—TensorFlow Federated (TFF), PySyft, and FedJAX—testing them on datasets like CIFAR-10 for image classification, IMDb reviews for sentiment analysis, and the UCI Heart Disease dataset for medical predictions. Our results show that TFF shines in image-related tasks with strong performance, while PySyft stands out for efficiently handling text data while keeping privacy intact. This research highlights FL’s promise in balancing data security with model performance, though challenges like communication delays and scaling still need to be tackled. As more devices connect and privacy concerns grow, improving these frameworks will be key to the future of machine learning innovation.
Authors: R. Sanjana, M. Nikesh, M. Bhuvaneshwari, M. Bharathi, T. Aditya Sai Srinivas
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6892950325
FWCI:
Cites:
Cited by:
Related to: