FedPC: Federated Learning for Language Generation with Personal and Context Preference Embeddings
This work addresses the need for efficient personalization in federated learning, particularly for conversational agents, though it appears incremental as it builds on existing personalization research.
The paper tackles the problem of personalizing federated learning systems for language generation by proposing a method that uses personal and context preference embeddings, resulting in a 50% improvement in test-time perplexity with significantly reduced memory usage.
Federated learning is a training paradigm that learns from multiple distributed users without aggregating data on a centralized server. Such a paradigm promises the ability to deploy machine-learning at-scale to a diverse population of end-users without first collecting a large, labeled dataset for all possible tasks. As federated learning typically averages learning updates across a decentralized population, there is a growing need for personalization of federated learning systems (i.e conversational agents must be able to personalize to a specific user's preferences). In this work, we propose a new direction for personalization research within federated learning, leveraging both personal embeddings and shared context embeddings. We also present an approach to predict these ``preference'' embeddings, enabling personalization without backpropagation. Compared to state-of-the-art personalization baselines, our approach achieves a 50\% improvement in test-time perplexity using 0.001\% of the memory required by baseline approaches, and achieving greater sample- and compute-efficiency.