Fetching the paper…
Reading the bibliography…
This white paper describes recent advances in Gboard(Google Keyboard)'s use of federated learning, DP-Follow-the-Regularized-Leader (DP-FTRL) algorithm, and secure aggregation techniques to train machine learning (ML) models for suggestion, prediction and correction intelligence from many users' typing data.
“Towards Federated Learning at Scale: System Design”
Kallista. Bonawitz, Hubert Eichner, Wolfgang Grieskamp, Dzmitry Huba, Alex Ingerman, Vladimir Ivanov, Chloé Kiddon, Jakub Konečný, Stefano Mazzocchi, H. McMahan, Timon Overveldt, David Petrou, Daniel Ramage and Jason Roselander · 1902
Earlier work this paper cites.
“Practical Secure Aggregation for Privacy-Preserving Machine Learning”
Keith Bonawitz, Vladimir Ivanov, Ben Kreuter, Antonio Marcedone, H. McMahan, Sarvar Patel, Daniel Ramage, Aaron Segal and Karn Seth · 2017
Earlier work this paper cites.
“Applied Federated Learning: Improving Google Keyboard Query Suggestions”
Timothy Yang, Galen Andrew, Hubert Eichner, Haicheng Sun, Wei Li, Nicholas Kong, Daniel Ramage and Françoise Beaufays · 2018
Earlier work this paper cites.
“Secure Single-Server Aggregation with (Poly)Logarithmic Overhead”
James Bell, Kallista. Bonawitz, Adrià Gascón, Tancrède Lepoint and Mariana Raykova · 2020
Earlier work this paper cites.
“Federated Learning and Privacy: Building Privacy-Preserving Systems for Machine Learning and Data Science on Decentralized Data”
Kallista Bonawitz, Peter Kairouz, Brendan McMahan and Daniel Ramage · 2021
Cited alongside, same era.
“The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation”
Peter Kairouz, Ziyu Liu and Thomas Steinke · 2021
Cited alongside, same era.
“The Skellam Mechanism for Differentially Private Federated Learning”
Naman Agarwal, Peter Kairouz and Ziyu Liu · 2021
Cited alongside, same era.
https://support.google.com/gboard/answer/12373137
Cited in the paper.
https://en.wikipedia.org/wiki/Multi-party_authorization
Cited in the paper.
https://www.tensorflow.org/federated/api_docs/python/tff/learning/ddp_secure_aggregator
“Practical and Private (Deep) Learning without Sampling or Shuffling”
Peter Kairouz, Brendan McMahan, Shuang Song, Om Thakkar, Abhradeep Thakurta and Zheng Xu · 2021
Later among the works it cites.
“Federated Learning with Formal Differential Privacy Guarantees” https://ai.googleblog.com/2022/02/federated-learning-with-formal.html , 2022
Brendan McMahan and Abhradeep Thakurta · 2022
Later among the works it cites.
“Federated Learning of Gboard Language Models with Differential Privacy”, 2023
Zheng Xu, Yanxiang Zhang, Galen Andrew, Christopher. Choquette-Choo, Peter Kairouz, H. McMahan, Jesse Rosenstock and Yuanbo Zhang · 2023
Closest in time.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Cited in the paper.
https://github.com/google/federated-compute/blob/main/fcp/client/http/http_federated_protocol.cc
Cited in the paper.
https://github.com/google/federated-compute/blob/main/fcp/client/grpc_federated_protocol.cc
Cited in the paper.
https://developer.android.com/google/play/integrity
Cited in the paper.
https://www.tensorflow.org/datasets/catalog/c4
Cited in the paper.
“Project Oak” https://github.com/project-oak/oak
Cited in the paper.
“Federated Aggregation” https://github.com/google/federated-compute/tree/main/fcp/aggregation
Cited in the paper.