A Survey on federated learning*
By Li Li, Yuxi Fan, Kuo-Yi Lin. 2020 IEEE 16th International Conference on Control & Automation (ICCA), 2020
878 citations recorded by the source corpus.
Federated learning (FL) is an emerging setting which implement machine learning in a distributed environment while protecting privacy. Research activities relating to FLhave grown at a fast rate recently in control. Exactly what activities have been carrying the research momentum forward is a question of interest to the research community. This study finds these research activities and optimization path of FL based on survey. Thus, this study aims to review related studies of FL to base on the baseline a universal definition gives a guiding for the future work. Besides, this study presents the prevailing FL applications and the evolution of federated learning. In the end, this study also identifies four research fronts to enrich the FL literature and help advance our understanding of the field. A comprehensive taxonomy of FL can also be developed through analyzing the results of this review.
Subfields: Artificial Intelligence, Computer Science Applications
View Paper: https://www.semanticscholar.org/paper/7dc04d1f17f1a71d684c01693d0de66fd6517f46
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
In Computer Science Applications
Citations in the corpus
- A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics (2023, neutral): “One potential solution to address this challenge is the adoption of Federated Learning (FL) [209], which enable the implementation of large-scale evaluation systems while preserving privacy.”
- Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch (2023, background): “This finding further confirms that SFT primarily unlocks the abilities of pre-trained LMs, rather than introducing new capabilities.”
- Privacy and Robustness in Federated Learning: Attacks and Defenses (2020, background): “Section III presents a comprehensive review of the privacy attacks in FL, particularly targeting the sensitive information (class representative, membership, properties, training inputs and labels) in HFL with homogeneous architectures.”
- Decentralized Federated Averaging (2021, background): “More details and applications of federated learning could be found in [17], [18].”