From distributed machine learning to federated learning: a survey
By Ji Liu, Jizhou Huang, Yang Zhou, Xuhong Li, Shilei Ji, Haoyi Xiong, Dejing Dou. Knowledge and Information Systems, 2021
358 citations recorded by the source corpus.
In recent years, data and computing resources are typically distributed in the devices of end users, various regions or organizations. Because of laws or regulations, the distributed data and computing resources cannot be aggregated or directly shared among different regions or organizations for machine learning tasks. Federated learning emerges as an efficient approach to exploit distributed data and computing resources, so as to collaboratively train machine learning models. At the same time, federated learning obeys the laws and regulations and ensures data security and data privacy. In this paper, we provide a comprehensive survey of existing works for federated learning. First, we propose a functional architecture of federated learning systems and a taxonomy of related techniques. Second, we explain the federated learning systems from four aspects: diverse types of parallelism, aggregation algorithms, data communication, and the security of federated learning systems. Third, we present four widely used federated systems based on the functional architecture. Finally, we summarize the limitations and propose future research directions.
Subfields: Artificial Intelligence
View Paper: https://www.semanticscholar.org/paper/f938cffd498ffb81ee9d66b4cd473e82c2e12c72
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
- Yong Xiang
- Mohammad R. Hayajneh
- Haftay Gebreslasie Abreha
- Chenhao Xu
- Mohamed Adel Serhani
- Longxiang Gao
- Youyang Qu
Citations in the corpus
- Federated Learning in Edge Computing: A Systematic Survey (2022, background): “…X X X X [18] Overview of current research trends and relevant challenges X X X X [83] Discussed the opportunities and challenges in FL X X X X [84] described the existing FL and proposed an architecture of FL systems X X X X [17] Described the different FL settings in more detail, emphasizing…”
- Asynchronous Federated Learning on Heterogeneous Devices: A Survey (2021, methodology): “FL is a kind of DML where local models are trained on distributed nodes, and the global model is generated on an aggregation server by averaging the local models [23, 24].”
- A survey on federated learning: challenges and applications (2022, background): “By combing the existing literature, we concluded that research on current FL mainly faces three bottlenecks: privacy and security threats, heterogeneity challenges, and huge communication overhead of FL [16].”