@inproceedings{rao-etal-2024-less,
title = "Less is Fed More: Sparsity Reduces Feature Distortion in Federated Learning",
author = "Rao, Abhinav and
Muhamed, Aashiq and
Diddee, Harshita",
editor = "Kumar, Sachin and
Balachandran, Vidhisha and
Park, Chan Young and
Shi, Weijia and
Hayati, Shirley Anugrah and
Tsvetkov, Yulia and
Smith, Noah and
Hajishirzi, Hannaneh and
Kang, Dongyeop and
Jurgens, David",
booktitle = "Proceedings of the 1st Workshop on Customizable NLP: Progress and Challenges in Customizing NLP for a Domain, Application, Group, or Individual (CustomNLP4U)",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.customnlp4u-1.4",
pages = "37--46",
abstract = "Our work studies Multilingual Federated Learning (FL), a decentralized paradigm that, although promising, grapples with issues such as client drift and suboptimal generalization in diverse, multilingual settings. We highlight limitations in existing approaches to generalize across both actively participating and inactive client language pairs. To mitigate these challenges, we introduce FedSparseNet, which incorporates sparse-network training, and LoRA, based on Low-Rank Adaptation. These approaches maintain the model{'}s fidelity to its pretraining distribution, thereby ensuring robust performance on both seen and unseen language pairs, while simultaneously enhancing communication efficiency by selectively transmitting trainable parameters. Our empirical evaluations demonstrate that FedSparseNet outperforms conventional FL models on both seen and unseen clients, while LoRA shows remarkable improvements in unseen client performance. Additionally, we propose the Continuous Relative Robustness Metric, a novel metric to uniformly assess a model{'}s performance across diverse language pairs. We open-source our code for reproducibility on GitHub.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rao-etal-2024-less">
<titleInfo>
<title>Less is Fed More: Sparsity Reduces Feature Distortion in Federated Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="family">Rao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aashiq</namePart>
<namePart type="family">Muhamed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harshita</namePart>
<namePart type="family">Diddee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Customizable NLP: Progress and Challenges in Customizing NLP for a Domain, Application, Group, or Individual (CustomNLP4U)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sachin</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vidhisha</namePart>
<namePart type="family">Balachandran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chan</namePart>
<namePart type="given">Young</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weijia</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shirley</namePart>
<namePart type="given">Anugrah</namePart>
<namePart type="family">Hayati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulia</namePart>
<namePart type="family">Tsvetkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noah</namePart>
<namePart type="family">Smith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hannaneh</namePart>
<namePart type="family">Hajishirzi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongyeop</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Our work studies Multilingual Federated Learning (FL), a decentralized paradigm that, although promising, grapples with issues such as client drift and suboptimal generalization in diverse, multilingual settings. We highlight limitations in existing approaches to generalize across both actively participating and inactive client language pairs. To mitigate these challenges, we introduce FedSparseNet, which incorporates sparse-network training, and LoRA, based on Low-Rank Adaptation. These approaches maintain the model’s fidelity to its pretraining distribution, thereby ensuring robust performance on both seen and unseen language pairs, while simultaneously enhancing communication efficiency by selectively transmitting trainable parameters. Our empirical evaluations demonstrate that FedSparseNet outperforms conventional FL models on both seen and unseen clients, while LoRA shows remarkable improvements in unseen client performance. Additionally, we propose the Continuous Relative Robustness Metric, a novel metric to uniformly assess a model’s performance across diverse language pairs. We open-source our code for reproducibility on GitHub.</abstract>
<identifier type="citekey">rao-etal-2024-less</identifier>
<location>
<url>https://aclanthology.org/2024.customnlp4u-1.4</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>37</start>
<end>46</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Less is Fed More: Sparsity Reduces Feature Distortion in Federated Learning
%A Rao, Abhinav
%A Muhamed, Aashiq
%A Diddee, Harshita
%Y Kumar, Sachin
%Y Balachandran, Vidhisha
%Y Park, Chan Young
%Y Shi, Weijia
%Y Hayati, Shirley Anugrah
%Y Tsvetkov, Yulia
%Y Smith, Noah
%Y Hajishirzi, Hannaneh
%Y Kang, Dongyeop
%Y Jurgens, David
%S Proceedings of the 1st Workshop on Customizable NLP: Progress and Challenges in Customizing NLP for a Domain, Application, Group, or Individual (CustomNLP4U)
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F rao-etal-2024-less
%X Our work studies Multilingual Federated Learning (FL), a decentralized paradigm that, although promising, grapples with issues such as client drift and suboptimal generalization in diverse, multilingual settings. We highlight limitations in existing approaches to generalize across both actively participating and inactive client language pairs. To mitigate these challenges, we introduce FedSparseNet, which incorporates sparse-network training, and LoRA, based on Low-Rank Adaptation. These approaches maintain the model’s fidelity to its pretraining distribution, thereby ensuring robust performance on both seen and unseen language pairs, while simultaneously enhancing communication efficiency by selectively transmitting trainable parameters. Our empirical evaluations demonstrate that FedSparseNet outperforms conventional FL models on both seen and unseen clients, while LoRA shows remarkable improvements in unseen client performance. Additionally, we propose the Continuous Relative Robustness Metric, a novel metric to uniformly assess a model’s performance across diverse language pairs. We open-source our code for reproducibility on GitHub.
%U https://aclanthology.org/2024.customnlp4u-1.4
%P 37-46
Markdown (Informal)
[Less is Fed More: Sparsity Reduces Feature Distortion in Federated Learning](https://aclanthology.org/2024.customnlp4u-1.4) (Rao et al., CustomNLP4U 2024)
ACL