Affiliation:
1. Banasthali Vidyapith, India
Abstract
Federated learning (FL) is closely linked to decentralized education. A decentralized system primarily targets expediting the operation phase, whereas federated learning concentrates on constructing a cooperative prototype devoid of privacy disclosure. Some of the most notable and frequently utilized FL-driven applications include Android's Keyboard for smart typing assistance and Google Virtual Assistant. FL can address data distributed across rows based on specimens and data spread across columns based on features in a cooperative training environment. This chapter explores the fundamental principles of FL, elucidating its foundational technologies and structures. In this chapter, categorization and its utilization for market scenarios in the fields of data analytics, medical care, learning, and business are examined. This chapter also pinpoints research forefronts to tackle federated learning and contribute to progressing our comprehension of Federated Learning for forthcoming enhancement.
Reference41 articles.
1. IOTFLA : A Secured and Privacy-Preserving Smart Home Architecture Implementing Federated Learning
2. Balta, D., Sellami, M., Kuhn, P., Schöpp, U., Buchinger, M., Baracaldo, N., . . .. (2021). Accountable federated machine learning in government: Engineering and management insights. In International conference on electronic participation (pp. 125–138). Springer.
3. Chen, Y., Ning, Y., & Rangwala, H. (2019). Asynchronous online federated learning for edge devices. ArXiv:1911.02134 [Cs]. Retrieved from http://arxiv.org/abs/1911.02134
4. Cheng, K., Fan, T., Jin, Y., Liu, Y., Chen, T., & Yang, Q. (2019). SecureBoost: A lossless federated learning framework.ArXiv:1901.08755 [Cs, Stat]. Retrieved from http://arxiv.org/abs/1901.08755