2019

Federated Evaluation of On-device Personalization

Wang, Kangkang, Mathews, Rajiv, Kiddon, Chloé et al.

Understand

Federated learning is a distributed, on-device computation framework that enables training global models without exporting sensitive user data to servers.

  • In this work, we describe methods to extend the federation framework to evaluate strategies for personalization of global models.
  • We present tools to analyze the effects of personalization and evaluate conditions under which personalization yields desirable models.
  • We report on our experiments personalizing a language model for a virtual keyboard for smartphones with a population of tens of millions of users.

Built on

  • A method for solving the convex programming problem with convergence rate o ⁡ ( 1 / k 2 ) o(1/{k}^{2})

    Yurii Nesterov. 1983 · 1983

    Earlier work this paper cites.

  • Long short-term memory

    S. Hochreiter and J. Schmidhuber. 1997 · 1997

    Earlier work this paper cites.

  • On the importance of initialization and momentum in deep learning

    Original

    Ilya Sutskever, James Martens, George Dahl, and Geoffrey Hinton. 2013 · 2013

    Earlier work this paper cites.

  • Technology device ownership: 2015

    Monica Anderson. 2015 · 2015

    Earlier work this paper cites.

  • Deep learning with differential privacy

    Martin Abadi, Andy Chu, Ian Goodfellow, H Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang. 2016b · 2016

    Earlier work this paper cites.

Similar

  • Tying word vectors and word classifiers: A loss framework for language modeling

    Original

    Hakan Inan, Khashayar Khosravi, and Richard Socher. 2016 · 2016

    Cited alongside, same era.

  • Practical secure aggregation for privacy-preserving machine learning

    Keith Bonawitz, Vladimir Ivanov, Ben Kreuter, Antonio Marcedone, H. Brendan McMahan, Sarvar Patel, Daniel Ramage, Aaron Segal, and Karn Seth. 2017 · 2017

    Cited alongside, same era.

  • LSTM: A search space odyssey

    Klaus Greff, Rupesh Kumar Srivastava, Jan Koutník, Bas R. Steunebrink, and Jürgen Schmidhuber. 2017 · 2017

    Cited alongside, same era.

  • Communication-efficient learning of deep networks from decentralized data

    Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Agüera y Arcas. 2017 · 2017

    Cited alongside, same era.

  • Using the output embedding to improve language models

    Ofir Press and Lior Wolf. 2017 · 2017

    Cited alongside, same era.

  • Tensorflow: A system for large-scale machine learning

    Martin Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, Manjunath Kudlur, Josh Levenberg, Rajat Monga, Sherry Moore, Derek G. Murray, Benoit Steiner, Paul Tucker, Vijay Vasudevan, Pete Warden, Martin Wicke, Yuan Yu, and Xiaoqiang Zheng. 2016a

    Cited in the paper.

Then

  • cpsgd: Communication-efficient and differentially-private distributed sgd

    Naman Agarwal, Ananda Theertha Suresh, Felix Yu, Sanjiv Kumar, and Brendan McMahan. 2018 · 2018

    Later among the works it cites.

  • Federated learning for mobile keyboard prediction

    Original

    Andrew Hard, Kanishka Rao, Rajiv Mathews, Françoise Beaufays, Sean Augenstein, Hubert Eichner, Chloé Kiddon, and Daniel Ramage. 2018 · 2018

    Later among the works it cites.

  • Learning differentially private recurrent language models

    Brendan McMahan, Daniel Ramage, Kunal Talwar, and Li Zhang. 2018 · 2018

    Later among the works it cites.

  • Towards federated learning at scale: System design

    Original

    Keith Bonawitz, Hubert Eichner, Wolfgang Grieskamp, Dzmitry Huba, Alex Ingerman, Vladimir Ivanov, Chloé M Kiddon, Jakub Konečný, Stefano Mazzocchi, Brendan McMahan, Timon Van Overveldt, David Petrou, Daniel Ramage, and Jason Roselander. 2019 · 2019

    Closest in time.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…