Get our free extension to see links to code for papers anywhere online!

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
Training Production Language Models without Memorizing User Data

Sep 21, 2020
Swaroop Ramaswamy, Om Thakkar, Rajiv Mathews, Galen Andrew, H. Brendan McMahan, Fran├žoise Beaufays


  Access Paper or Ask Questions

Understanding Unintended Memorization in Federated Learning

Jun 12, 2020
Om Thakkar, Swaroop Ramaswamy, Rajiv Mathews, Fran├žoise Beaufays


  Access Paper or Ask Questions

Training Keyword Spotting Models on Non-IID Data with Federated Learning

Jun 04, 2020
Andrew Hard, Kurt Partridge, Cameron Nguyen, Niranjan Subrahmanya, Aishanee Shah, Pai Zhu, Ignacio Lopez Moreno, Rajiv Mathews

* Submitted to Interspeech 2020 

  Access Paper or Ask Questions

Generative Models for Effective ML on Private, Decentralized Datasets

Nov 15, 2019
Sean Augenstein, H. Brendan McMahan, Daniel Ramage, Swaroop Ramaswamy, Peter Kairouz, Mingqing Chen, Rajiv Mathews, Blaise Aguera y Arcas

* 27 pages, 8 figures 

  Access Paper or Ask Questions

Federated Evaluation of On-device Personalization

Oct 22, 2019
Kangkang Wang, Rajiv Mathews, Chlo├ę Kiddon, Hubert Eichner, Fran├žoise Beaufays, Daniel Ramage

* 4 pages, 4 figures 

  Access Paper or Ask Questions

Federated Learning of N-gram Language Models

Oct 08, 2019
Mingqing Chen, Ananda Theertha Suresh, Rajiv Mathews, Adeline Wong, Cyril Allauzen, Fran├žoise Beaufays, Michael Riley

* 10 pages 

  Access Paper or Ask Questions

Federated Learning for Emoji Prediction in a Mobile Keyboard

Jun 11, 2019
Swaroop Ramaswamy, Rajiv Mathews, Kanishka Rao, Fran├žoise Beaufays


  Access Paper or Ask Questions

Federated Learning Of Out-Of-Vocabulary Words

Mar 26, 2019
Mingqing Chen, Rajiv Mathews, Tom Ouyang, Fran├žoise Beaufays


  Access Paper or Ask Questions

Federated Learning for Mobile Keyboard Prediction

Nov 08, 2018
Andrew Hard, Kanishka Rao, Rajiv Mathews, Fran├žoise Beaufays, Sean Augenstein, Hubert Eichner, Chlo├ę Kiddon, Daniel Ramage

* 7 pages, 4 figures 

  Access Paper or Ask Questions