@inproceedings{agarwal-etal-2023-practical,
title = "Practical Takes on Federated Learning with Pretrained Language Models",
author = "Agarwal, Ankur and
Rezagholizadeh, Mehdi and
Parthasarathi, Prasanna",
editor = "Vlachos, Andreas and
Augenstein, Isabelle",
booktitle = "Findings of the Association for Computational Linguistics: EACL 2023",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-eacl.34/",
doi = "10.18653/v1/2023.findings-eacl.34",
pages = "454--471",
abstract = "Real-world applications of language models entail data privacy constraints when learning from diverse data domains. Federated learning with pretrained language models for language tasks has been gaining attention lately but there are definite confounders that warrants a careful study. Specifically, understanding the limits of federated NLP applications through varying the effects of different aspects (such as data heterogeneity, the trade-off between training time and performance, the effect of different data, and client distributions and sensitivity of the shared model to learning local distributions) is necessary to evaluate whether language models indeed learn to generalize by adapting to the different domains. Towards that, we elaborate different hypotheses over the components in federated NLP architectures and study them in detail with relevant experiments over three tasks: Stanford Sentiment Treebank-2, OntoNotes-5.0 and GigaWord. The experiments with different Transformer inductive biases on the variety of tasks provide a glimpse at the understanding of federated learning at NLP tasks. Specifically, the analysis suggests that regularization due to the ensembling effect may be masquerading as domain adaptation of federated learning in NLP with pre-trained language models."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="agarwal-etal-2023-practical">
<titleInfo>
<title>Practical Takes on Federated Learning with Pretrained Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ankur</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehdi</namePart>
<namePart type="family">Rezagholizadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prasanna</namePart>
<namePart type="family">Parthasarathi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andreas</namePart>
<namePart type="family">Vlachos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isabelle</namePart>
<namePart type="family">Augenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Real-world applications of language models entail data privacy constraints when learning from diverse data domains. Federated learning with pretrained language models for language tasks has been gaining attention lately but there are definite confounders that warrants a careful study. Specifically, understanding the limits of federated NLP applications through varying the effects of different aspects (such as data heterogeneity, the trade-off between training time and performance, the effect of different data, and client distributions and sensitivity of the shared model to learning local distributions) is necessary to evaluate whether language models indeed learn to generalize by adapting to the different domains. Towards that, we elaborate different hypotheses over the components in federated NLP architectures and study them in detail with relevant experiments over three tasks: Stanford Sentiment Treebank-2, OntoNotes-5.0 and GigaWord. The experiments with different Transformer inductive biases on the variety of tasks provide a glimpse at the understanding of federated learning at NLP tasks. Specifically, the analysis suggests that regularization due to the ensembling effect may be masquerading as domain adaptation of federated learning in NLP with pre-trained language models.</abstract>
<identifier type="citekey">agarwal-etal-2023-practical</identifier>
<identifier type="doi">10.18653/v1/2023.findings-eacl.34</identifier>
<location>
<url>https://aclanthology.org/2023.findings-eacl.34/</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>454</start>
<end>471</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Practical Takes on Federated Learning with Pretrained Language Models
%A Agarwal, Ankur
%A Rezagholizadeh, Mehdi
%A Parthasarathi, Prasanna
%Y Vlachos, Andreas
%Y Augenstein, Isabelle
%S Findings of the Association for Computational Linguistics: EACL 2023
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F agarwal-etal-2023-practical
%X Real-world applications of language models entail data privacy constraints when learning from diverse data domains. Federated learning with pretrained language models for language tasks has been gaining attention lately but there are definite confounders that warrants a careful study. Specifically, understanding the limits of federated NLP applications through varying the effects of different aspects (such as data heterogeneity, the trade-off between training time and performance, the effect of different data, and client distributions and sensitivity of the shared model to learning local distributions) is necessary to evaluate whether language models indeed learn to generalize by adapting to the different domains. Towards that, we elaborate different hypotheses over the components in federated NLP architectures and study them in detail with relevant experiments over three tasks: Stanford Sentiment Treebank-2, OntoNotes-5.0 and GigaWord. The experiments with different Transformer inductive biases on the variety of tasks provide a glimpse at the understanding of federated learning at NLP tasks. Specifically, the analysis suggests that regularization due to the ensembling effect may be masquerading as domain adaptation of federated learning in NLP with pre-trained language models.
%R 10.18653/v1/2023.findings-eacl.34
%U https://aclanthology.org/2023.findings-eacl.34/
%U https://doi.org/10.18653/v1/2023.findings-eacl.34
%P 454-471
Markdown (Informal)
[Practical Takes on Federated Learning with Pretrained Language Models](https://aclanthology.org/2023.findings-eacl.34/) (Agarwal et al., Findings 2023)
ACL