Federated learning is a training paradigm that learns from multiple distributed users without aggregating data on a centralized server, promising the ability to deploy machine-learning to a diverse population of users without first collecting large, labeled datasets. As federated learning involves averaging gradient updates across a decentralized population, there is a growing need for personalization of federated learning systems (i.e. conversational agents must personalize to individual users and the context of an interaction).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.

The ease of access to pre-trained transformers has enabled developers to leverage large-scale language models to build exciting applications for their users. While such pre-trained models offer convenient starting points for researchers and developers, there is little consideration for the societal biases captured within these model risking perpetuation of racial, gender, and other harmful biases when these models are deployed at scale. In this paper, we investigate gender and racial bias across ubiquitous pre-trained language models, including GPT-2, XLNet, BERT, RoBERTa, ALBERT and DistilBERT. We evaluate bias within pre-trained transformers using three metrics: WEAT, sequence likelihood, and pronoun ranking. We conclude with an experiment demonstrating the ineffectiveness of word-embedding techniques, such as WEAT, signaling the need for more robust bias testing in transformers.