Title:Federated Learning: An Approach for Managing Data Privacy and Security in Collaborative Learning
Volume: 18
Author(s): Reeti Jaswal, Surya Narayan Panda and Vikas Khullar*
Affiliation:
- Computer Science and Engineering, Chitkara University Institute of Engineering and Technology, Chitkara University,
Chandigarh, Rajpura, Punjab, India
Keywords:
Federated learning, healthcare, IoT, machine learning mobile devices, privacy, security issues.
Abstract: In the field of machine learning, federated learning (FL) has become a breakthrough
paradigm, provided a decentralized method of training models while solving issues with data security,
privacy, and scalability. This study offers a thorough analysis of FL, including an examination
of its underlying theories, its varieties, and a comparison with more conventional machine
learning techniques. We explore the drawbacks of conventional machine learning techniques, especially
when sensitive and distributed data is involved. We also explain how FL addresses these
drawbacks by leveraging collaborative learning across decentralized devices or servers. We also
highlight the various fields in which FL finds application, including healthcare, industries, IoT,
mobile devices, and education, demonstrating its potential to deliver tailored services and predictive
analytics while maintaining data privacy. Furthermore, we address the main obstacles to FL
adoption, such as costly communication, heterogeneous systems, statistical heterogeneity, and
privacy concerns, and we suggest possible directions for future research to effectively overcome
these obstacles. In order to facilitate future study and growth in this quickly developing discipline,
this review attempts to shed light on the advances and challenges of FL.
