Research References

Federated Learning References by Google

Research

• [Federated Averaging] Communication-Efficient Learning of Deep Networks from Decentralized Data
• [System design] Towards Federated Learning at Scale: System Design
• [Differential Privacy] Learning Differentially Private Recurrent Language Models
• [Differential Privacy] A General Approach to Adding Differential Privacy to Iterative Training Procedures
• [Differential Privacy] Federated Heavy Hitters Discovery with Differential Privacy
• [Efficiency] Federated Learning: Strategies for Improving Communication Efficiency
• [Efficiency] Distributed Mean Estimation with Limited Communication
• [Efficiency] cpSGD: Communication-efficient and differentially-private distributed SGD
• [Efficiency] Expanding the Reach of Federated Learning by Reducing Client Resource Requirements
• [Learning theory] Agnostic Federated Learning
• [Optimization] Graph Oracle Models, Lower Bounds, and Gaps for Parallel Stochastic Optimization
• [Optimization] Federated Optimization: Distributed Machine Learning for On-Device Intelligence
• [Security] Practical Secure Aggregation for Privacy Preserving Machine Learning

Production use for language modelling

• Federated Learning for Mobile Keyboard Prediction
• Applied Federated Learning: Improving Google Keyboard Query Suggestions
• Federated Learning Of Out-Of-Vocabulary Words

TensorFlow Federated

An open-source framework for machine learning and other computations on decentralized data.

www.tensorflow.org/federated