Federated Learning: A Survey on Enabling Technologies, Protocols, and Applications

By Mohammed Aledhari, Rehma Razzak, R. Parizi, Fahad Saeed. IEEE Access, 2020

618 citations recorded by the source corpus.

This paper provides a comprehensive study of Federated Learning (FL) with an emphasis on enabling software and hardware platforms, protocols, real-life applications and use-cases. FL can be applicable to multiple domains but applying it to different industries has its own set of obstacles. FL is known as collaborative learning, where algorithm(s) get trained across multiple devices or servers with decentralized data samples without having to exchange the actual data. This approach is radically different from other more established techniques such as getting the data samples uploaded to servers or having data in some form of distributed infrastructure. FL on the other hand generates more robust models without sharing data, leading to privacy-preserved solutions with higher security and access privileges to data. This paper starts by providing an overview of FL. Then, it gives an overview of technical details that pertain to FL enabling technologies, protocols, and applications. Compared to other survey papers in the field, our objective is to provide a more thorough summary of the most relevant protocols, platforms, and real-life use-cases of FL to enable data scientists to build better privacy-preserving solutions for industries in critical need of FL. We also provide an overview of key challenges presented in the recent literature and provide a summary of related research work. Moreover, we explore both the challenges and advantages of FL and present detailed service use-cases to illustrate how different architectures and protocols that use FL can fit together to deliver desired results.

Subfields: Artificial Intelligence, Computer Science Applications

View Paper: https://www.semanticscholar.org/paper/e00c69fb70095b92ac3c0bb0c1d737dfa696d232

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Hangyu Zhu
2. Mingzhe Chen
3. H. Vincent Poor
4. Qinbin Li
5. Bingsheng He
6. Zhaohui Yang
7. Shuguang Cui
8. Zhaomin Wu

In Computer Science Applications

1. Shiqing Liu
2. Jinjin Xu
3. Yaochu Jin
4. Hangyu Zhu
5. Bingsheng He
6. H. Vincent Poor
7. Qinbin Li

Citations in the corpus

• Structured Pruning for Deep Convolutional Neural Networks: A Survey (2023, background): “Pruning for Federated Learning: Federated learning [277] aims to solve the problem of training a model without transferring data to a central location.”
• Federated Learning in Edge Computing: A Systematic Survey (2022, background): “Furthermore, References [137,138] also proposed a proactive caching scheme by leveraging FL in the edge computing paradigm.”
• Federated Learning: Opportunities and Challenges (2021, background): “The recent works [2, 14, 26, 36] are focused either on different federated learning architecture or on different challenges in FL domain.”
• Federated Learning on Non-IID Data: A Survey (2021, background): “The client with data labels are called guest party [1] (client) or passive party [19] (client), whereas the client without data labels are termed host party (client) or active party (client).”
• Federated Learning for Internet of Things: A Comprehensive Survey (2021, background): “[14] FL concept A survey on the FL hardware, software, platforms, and protocols with limited discussion of FL-based healthcare use cases.”
• Federated Learning for 6G: Applications, Challenges, and Opportunities (2021, background): “[30], including applications, usage scenarios, and hardware platforms.”
• A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection (2019, background): “More recently, another survey [10] summarizes the platforms, protocols and applications of federated learning.”