@inproceedings{passban-etal-2022-training,
title = "Training Mixed-Domain Translation Models via Federated Learning",
author = "Passban, Peyman and
Roosta, Tanya and
Gupta, Rahul and
Chadha, Ankit and
Chung, Clement",
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.186",
doi = "10.18653/v1/2022.naacl-main.186",
pages = "2576--2586",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="passban-etal-2022-training">
<titleInfo>
<title>Training Mixed-Domain Translation Models via Federated Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Peyman</namePart>
<namePart type="family">Passban</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanya</namePart>
<namePart type="family">Roosta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rahul</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ankit</namePart>
<namePart type="family">Chadha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Clement</namePart>
<namePart type="family">Chung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">passban-etal-2022-training</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-main.186</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-main.186</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>2576</start>
<end>2586</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Training Mixed-Domain Translation Models via Federated Learning
%A Passban, Peyman
%A Roosta, Tanya
%A Gupta, Rahul
%A Chadha, Ankit
%A Chung, Clement
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F passban-etal-2022-training
%X 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.
%R 10.18653/v1/2022.naacl-main.186
%U https://aclanthology.org/2022.naacl-main.186
%U https://doi.org/10.18653/v1/2022.naacl-main.186
%P 2576-2586
Markdown (Informal)
[Training Mixed-Domain Translation Models via Federated Learning](https://aclanthology.org/2022.naacl-main.186) (Passban et al., NAACL 2022)
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.