Federated Learning for Emoji Prediction in a Mobile Keyboard

Abstract

We show that a word-level recurrent neural network can predict emoji from text typed on a mobile keyboard. We demonstrate the usefulness of transfer learning for predicting emoji by pretraining the model using a language modeling task. We also propose mechanisms to trigger emoji and tune the diversity of candidates. The model is trained using a distributed on-device learning framework called federated learning. The federated model is shown to achieve better performance than a server-trained model. This work demonstrates the feasibility of using federated learning to train production-quality models for natural language understanding tasks while keeping users' data on their devices.

Cited by in corpus (12)

• FMore: An Incentive Scheme of Multi-dimensional Auction for Federated Learning in MEC
• Edge Intelligence: Architectures, Challenges, and Applications
• Training Speech Recognition Models with Federated Learning: A Quality/Cost Framework
• The Internet of Federated Things (IoFT): A Vision for the Future and In-depth Survey of Data-driven Approaches for Federated Learning
• Towards Efficient Synchronous Federated Training: A Survey on System Optimization Strategies
• Multi-Model Federated Learning
• Contrastive encoder pre-training-based clustered federated learning for heterogeneous data
• Byzantines can also Learn from History: Fall of Centered Clipping in Federated Learning
• Self-supervised Cross-silo Federated Neural Architecture Search
• FedSkel: Efficient Federated Learning on Heterogeneous Systems with Skeleton Gradients Update
• VoiceMoji: A Novel On-Device Pipeline for Seamless Emoji Insertion in Dictation
• A Communication-efficient Local Differentially Private Algorithm in Federated Optimization