A Survey on Federated Learning: The Journey From Centralized to Distributed On-Site Learning and Beyond

Abdulrahman, Sawsan; Tout, Hanine; Ould-Slimane, Hakima; Mourad, Azzam; Talhi, Chamseddine; Guizani, Mohsen

doi:10.1109/jiot.2020.3030072

Cited by 433 publications

(209 citation statements)

References 66 publications

Supporting

Mentioning

150

Contrasting

Order By: Relevance

“…•Cloud computing security attacks [154] •Protect privacy in Blockchain through federated learning [155] •Try to build a deep learning model using Blockchain [156] •Fusion of Blockchain and distributed learning [157] Cloud technology…”

Section: E Future Research Directionsmentioning

confidence: 99%

Bibliometric Analysis of the Blockchain Scientific Evolution: 2014–2020

Luo

Bai

2021

IEEE Access

View full text Add to dashboard Cite

As one of the disruptive technologies in the fourth industrial revolution, Blockchain has irrevocably changed how people live and work. Many scholars have studied the Blockchain, and the number of related publications has increased over time. Bibliometrics is an excellent method to study the development trend of a specific field. However, few scholars have used bibliometrics to research Blockchain; the inheritance and evolution among its different research themes have not yet been fully understood. This study emphasizes the scientific evolution and research focus of Blockchain through bibliometric analysis. We analyzed 2993 publications from 2014 to 2020 using co-word analysis and cluster analysis with bibliometric tools such as the SciMAT. The most productive author, country, institutions and leading research areas were identified, outlining the Blockchain field's fundamental developments. The results show the changes in keywords regarding Blockchain summarize the research hotspots in different periods. The study discusses the evolution process of various themes in each period, providing a meaningful reference for scholars to identify research hotspots and future research directions in the Blockchain field.

show abstract

Section: E Future Research Directionsmentioning

confidence: 99%

Bibliometric Analysis of the Blockchain Scientific Evolution: 2014–2020

Luo

Bai

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Additionally, refs. [ 14 , 15 , 16 ] are other domain-agnostic surveys about federated learning that define FL, its different architectures, algorithms, challenges, and applications. We also find surveys about the integration of the futuristic 6G network with FL, such as in [ 14 ], where the authors describe key technical challenges of such integration.…”

Section: Major Contributions Of the Papermentioning

confidence: 99%

Rebirth of Distributed AI—A Review of eHealth Research

Khan

Alkaabi

2021

Sensors

View full text Add to dashboard Cite

The envisioned smart city domains are expected to rely heavily on artificial intelligence and machine learning (ML) approaches for their operations, where the basic ingredient is data. Privacy of the data and training time have been major roadblocks to achieving the specific goals of each application domain. Policy makers, the research community, and the industrial sector have been putting their efforts into addressing these issues. Federated learning, with its distributed and local training approach, stands out as a potential solution to these challenges. In this article, we discuss the potential interplay of different technologies and AI for achieving the required features of future smart city services. Having discussed a few use-cases for future eHealth, we list design goals and technical requirements of the enabling technologies. The paper confines its focus on federated learning. After providing the tutorial on federated learning, we analyze the Federated Learning research literature. We also highlight the challenges. A solution sketch and high-level research directions may be instrumental in addressing the challenges.

show abstract

“…Moving to the network limitation problem and emergency of low-latency applications requiring fast analysis, the fact that the cloud data centers are often deployed in locations that are far from those of the data owners leads to high data processing delays due to the long-distance communications. In the light of these two crucial factors, the trend in data storage and analysis is shifting from being cloud-based and centralized to being distributed and on-device [4], [5]. The key enabler technology for such a shift is that of edge computing [6], [7], wherein edge nodes such as smartphones, sensor, micro servers, autonomous vehicles and home gateways are supplied with computing and storage capabilities to enable them to host and analyze data locally within minimal delay.…”

Section: Introductionmentioning

confidence: 99%

Federated Machine Learning: Survey, Multi-Level Classification, Desirable Criteria and Future Directions in Communication and Networking Systems

Wahab

Mourad

Otrok

et al. 2021

IEEE Commun. Surv. Tutorials

Self Cite

340

110

View full text Add to dashboard Cite

The communication and networking field is hungry for machine learning decision-making solutions to replace the traditional model-driven approaches that proved to be not rich enough for seizing the ever-growing complexity and heterogeneity of the modern systems in the field. Traditional machine learning solutions assume the existence of (cloud-based) central entities that are in charge of processing the data. Nonetheless, the difficulty of accessing private data, together with the high cost of transmitting raw data to the central entity gave rise to a decentralized machine learning approach called Federated Learning. The main idea of federated learning is to perform an on-device collaborative training of a single machine learning model without having to share the raw training data with any third-party entity. Although few survey articles on federated learning already exist in the literature, the motivation of this survey stems from three essential observations. The first one is the lack of a fine-grained multi-level classification of the federated learning literature, where the existing surveys base their classification on only one criterion or aspect. The second observation is that the existing surveys focus only on some common challenges, but disregard other essential aspects such as reliable client selection, resource management and training service pricing. The third observation is the lack of explicit and straightforward directives for researchers to help them design future federated learning solutions that overcome the state-of-the-art research gaps. To address these points, we first provide a comprehensive tutorial on federated learning and its associated concepts, technologies and learning approaches. We then survey and highlight the applications and future directions of federated learning in the domain of communication and networking. Thereafter, we design a three-level classification scheme that first categorizes the federated learning literature based on the high-level challenge that they tackle. Then, we classify each high-level challenge into a set of specific low-level challenges to foster a better understanding of the topic. Finally, we provide, within each low-level challenge, a fine-grained classification based on the technique used to address this particular challenge. For each category of high-level challenges, we provide a set of desirable criteria and future research directions that are aimed to help the research community design innovative and efficient future solutions. To the best of our knowledge, our survey is the most comprehensive in terms of challenges and techniques it covers and the most fine-grained in terms of the multi-level classification scheme it presents.

show abstract

A Survey on Federated Learning: The Journey From Centralized to Distributed On-Site Learning and Beyond

Cited by 433 publications

References 66 publications

Bibliometric Analysis of the Blockchain Scientific Evolution: 2014–2020

Bibliometric Analysis of the Blockchain Scientific Evolution: 2014–2020

Rebirth of Distributed AI—A Review of eHealth Research

Federated Machine Learning: Survey, Multi-Level Classification, Desirable Criteria and Future Directions in Communication and Networking Systems

Contact Info

Product

Resources

About