Federated Learning Meets Natural Language Processing: A Survey

TL;DR

This survey reviews how federated learning is applied to natural language processing, addressing challenges, evaluation methods, and future research directions in privacy-preserving NLP models.

Contribution

It provides a comprehensive overview of federated NLP techniques, challenges, evaluation tools, and identifies key research gaps and future directions.

Findings

Federated NLP faces significant algorithm and system challenges.

Current evaluation methods for federated NLP are limited and need improvement.

Future research should focus on privacy, efficiency, and robustness in federated NLP.

Abstract

Federated Learning aims to learn machine learning models from multiple decentralized edge devices (e.g. mobiles) or servers without sacrificing local data privacy. Recent Natural Language Processing techniques rely on deep learning and large pre-trained language models. However, both big deep neural and language models are trained with huge amounts of data which often lies on the server side. Since text data is widely originated from end users, in this work, we look into recent NLP models and techniques which use federated learning as the learning framework. Our survey discusses major challenges in federated natural language processing, including the algorithm challenges, system challenges as well as the privacy issues. We also provide a critical review of the existing Federated NLP evaluation methods and tools. Finally, we highlight the current research gaps and future directions.