Pretrained Models for Multilingual Federated Learning
Orion Weller, Marc Marone, Vladimir Braverman, Dawn Lawrie, Benjamin Van Durme
Abstract
Since the advent of Federated Learning (FL), research has applied these methods to natural language processing (NLP) tasks. Despite a plethora of papers in FL for NLP, no previous works have studied how multilingual text impacts FL algorithms. Furthermore, multilingual text provides an interesting avenue to examine the impact of non-IID text (e.g. different languages) on FL in naturally occurring data. We explore three multilingual language tasks, language modeling, machine translation, and text classification using differing federated and non-federated learning algorithms. Our results show that using pretrained models reduces the negative effects of FL, helping them to perform near or better than centralized (no privacy) learning, even when using non-IID partitioning.
BibTeX
@inproceedings{weller-etal-2022-pretrained,
title = "Pretrained Models for Multilingual Federated Learning",
author = "Weller, Orion and
Marone, Marc and
Braverman, Vladimir and
Lawrie, Dawn and
Van Durme, Benjamin",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.101/",
doi = "10.18653/v1/2022.naacl-main.101",
pages = "1413--1421"
}