Applied Federated Learning: Improving Google Keyboard Query Suggestions

2018/12/07 by Timothy T. Yang, Timothy Yang, Galen Andrew +14 · 21 citations
Computer Science · Mathematics · Social Sciences · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Mobile Crowdsensing and Crowdsourcing #Privacy, Security, and Data Protection #Privacy-Preserving Technologies in Data #cs.LG #stat.ML

paper · pdf · doi:10.48550/arxiv.1812.02903

arxiv created 2018/12/07 · openalex publication_date 2018/12/07 · arxiv updated 2018/12/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Federated learning is a distributed form of machine learning where both the training data and model training are decentralized. In this paper, we use federated learning in a commercial, global-scale setting to train, evaluate and deploy a model to improve virtual keyboard search suggestion quality without direct access to the underlying user data. We describe our observations in federated training, compare metrics to live deployments, and present resulting quality increases. In whole, we demonstrate how federated learning can be applied end-to-end to both improve user experiences and enhance user privacy.

Citations

• Long Short-Term Memory
• Federated Optimization: Distributed Machine Learning for On-Device Intelligence

Cited by

• Optimal Key Rates for Decentralized Secure Aggregation with Arbitrary Collusion and Heterogeneous Security Constraints
• The Capacity of Collusion-Resilient Decentralized Secure Aggregation with Groupwise Keys
• FedPoP: Federated Learning Meets Proof of Participation
• Federated Learning via Meta-Variational Dropout
• Local Differential Privacy for Federated Learning with Fixed Memory Usage and Per-Client Privacy
• Research in Collaborative Learning Does Not Serve Cross-Silo Federated Learning in Practice
• FedERL: Federated Efficient and Robust Learning for Common Corruptions
• The MICCAI Federated Tumor Segmentation (FeTS) Challenge 2024: Efficient and Robust Aggregation Methods
• FedCD: A Fairness-aware Federated Cognitive Diagnosis Framework
• Information-Theoretic Decentralized Secure Aggregation with Passive Collusion Resilience
• Hierarchical Secure Aggregation with Heterogeneous Security Constraints and Arbitrary User Collusion
• Domain Borders Are There to Be Crossed With Federated Few-Shot Adaptation
• Federated Learning from Molecules to Processes: A Perspective
• The Federated Tumor Segmentation (FeTS) Challenge
• Label Leakage in Federated Inertial-based Human Activity Recognition
• FedJAX: Federated learning simulation with JAX
• Management of Resource at the Network Edge for Federated Learning
• Generative Models for Effective ML on Private, Decentralized Datasets
• Secure Federated Submodel Learning
• Data-Free Evaluation of User Contributions in Federated Learning
• A Systematic Literature Review on Federated Learning: From A Model Quality Perspective
• SparsyFed: Sparse Adaptive Federated Training
• Learning, Computing, and Trustworthiness in Intelligent IoT Environments: Performance-Energy Tradeoffs

Related

• Federated Learning for Ranking Browser History Suggestions
• Private Federated Learning in Gboard
• Federated Reconstruction: Partially Local Federated Learning
• Production federated keyword spotting via distillation, filtering, and joint federated-centralized training
• FEL: High Capacity Learning for Recommendation and Ranking via Federated Ensemble Learning