Corpus ID: 59599820

Towards Federated Learning at Scale: System Design

@article{Bonawitz2019TowardsFL,
  title={Towards Federated Learning at Scale: System Design},
  author={Keith Bonawitz and Hubert Eichner and Wolfgang Grieskamp and Dzmitry Huba and Alex Ingerman and Vladimir Ivanov and Chlo{\'e} Kiddon and Jakub Konecn{\'y} and Stefano Mazzocchi and H. Brendan McMahan and Timon Van Overveldt and David Petrou and Daniel Ramage and Jason Roselander},
  journal={ArXiv},
  year={2019},
  volume={abs/1902.01046}
}
  • Keith Bonawitz, Hubert Eichner, +11 authors Jason Roselander
  • Published 2019
  • Computer Science, Mathematics
  • ArXiv
  • Federated Learning is a distributed machine learning approach which enables model training on a large corpus of decentralized data. We have built a scalable production system for Federated Learning in the domain of mobile devices, based on TensorFlow. In this paper, we describe the resulting high-level design, sketch some of the challenges and their solutions, and touch upon the open problems and future directions. 

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 240 CITATIONS, ESTIMATED 100% COVERAGE

    Advances and Open Problems in Federated Learning

    VIEW 2 EXCERPTS
    CITES BACKGROUND

    Industrial Federated Learning - Requirements and System Design

    VIEW 8 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Federated Learning: Challenges, Methods, and Future Directions

    VIEW 16 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Adaptive Federated Optimization

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Clustered Federated Learning

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Survey of Personalization Techniques for Federated Learning

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Multi-Center Federated Learning

    VIEW 1 EXCERPT
    CITES BACKGROUND

    FILTER CITATIONS BY YEAR

    2018
    2020

    CITATION STATISTICS

    • 25 Highly Influenced Citations

    • Averaged 80 Citations per year from 2018 through 2020

    • 30% Increase in citations per year in 2020 over 2019

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 24 REFERENCES

    Federated learning of predictive models from federated Electronic Health Records

    VIEW 1 EXCERPT

    Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge

    VIEW 1 EXCERPT

    Scaling Distributed Machine Learning with the Parameter Server

    VIEW 1 EXCERPT