Training Mixed-Domain Translation Models via Federated Learning

Peyman Passban, Tanya Roosta, Rahul Gupta, Ankit Chadha, Clement Chung


Abstract
Training mixed-domain translation models is a complex task that demands tailored architec- tures and costly data preparation techniques. In this work, we leverage federated learning (FL) in order to tackle the problem. Our investiga- tion demonstrates that with slight modifications in the training process, neural machine trans- lation (NMT) engines can be easily adapted when an FL-based aggregation is applied to fuse different domains. Experimental results also show that engines built via FL are able to perform on par with state-of-the-art baselines that rely on centralized training techniques. We evaluate our hypothesis in the presence of five datasets with different sizes, from different domains, to translate from German into English and discuss how FL and NMT can mutually benefit from each other. In addition to provid- ing benchmarking results on the union of FL and NMT, we also propose a novel technique to dynamically control the communication band- width by selecting impactful parameters during FL updates. This is a significant achievement considering the large size of NMT engines that need to be exchanged between FL parties.
Anthology ID:
2022.naacl-main.186
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Editors:
Marine Carpuat, Marie-Catherine de Marneffe, Ivan Vladimir Meza Ruiz
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2576–2586
Language:
URL:
https://aclanthology.org/2022.naacl-main.186
DOI:
10.18653/v1/2022.naacl-main.186
Bibkey:
Cite (ACL):
Peyman Passban, Tanya Roosta, Rahul Gupta, Ankit Chadha, and Clement Chung. 2022. Training Mixed-Domain Translation Models via Federated Learning. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2576–2586, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
Training Mixed-Domain Translation Models via Federated Learning (Passban et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.186.pdf
Video:
 https://aclanthology.org/2022.naacl-main.186.mp4