Federated Learning (FL) is a novel machine learning approach that allows the model trainer to access more data samples, by training the model across multiple decentralized data sources, while data access constraints are in place.
Privacy concerns have attracted increasing attention in data-driven products and services.
In this work, we propose a novel ensemble knowledge transfer method named Fed-ET in which small models (different in architecture) are trained on clients, and used to train a larger model at the server.
We compare the platform with other state-of-the-art platforms and describe available features of FLUTE for experimentation in core areas of active research, such as optimization, privacy, and scalability.
As such, these models are often unable to produce personalized responses for individual users, based on their data.
Auditing NLP systems for computational harms like surfacing stereotypes is an elusive goal.
In this work, we introduce two privacy-preserving regularization methods for training language models that enable joint optimization of utility and privacy through (1) the use of a discriminator and (2) the inclusion of a novel triplet-loss term.
We propose a model that captures the correlation in the social network graph, and incorporates this correlation in the privacy calculations through Pufferfish privacy principles.
In this work, we introduce two privacy-preserving regularization methods for training language models that enable joint optimization of utility and privacy through (1) the use of a discriminator and (2) the inclusion of a triplet-loss term.
It has been demonstrated that strong performance of language models comes along with the ability to memorize rare training samples, which poses serious privacy threats in case the model is trained on confidential user content.
We show that leveraging metadata information from web pages can improve the performance of models for answer passage selection/reranking.
Our contributions are three-fold: (1) We first present a survey to understand the space of document-centered assistance and the capabilities people expect in this scenario.