@inproceedings{chen-etal-2022-actperfl,
title = "{A}ct{P}er{FL}: Active Personalized Federated Learning",
author = "Chen, Huili and
Ding, Jie and
Tramel, Eric and
Wu, Shuang and
Sahu, Anit Kumar and
Avestimehr, Salman and
Zhang, Tao",
editor = "Lin, Bill Yuchen and
He, Chaoyang and
Xie, Chulin and
Mireshghallah, Fatemehsadat and
Mehrabi, Ninareh and
Li, Tian and
Soltanolkotabi, Mahdi and
Ren, Xiang",
booktitle = "Proceedings of the First Workshop on Federated Learning for Natural Language Processing (FL4NLP 2022)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.fl4nlp-1.1",
doi = "10.18653/v1/2022.fl4nlp-1.1",
pages = "1--5",
abstract = "In the context of personalized federated learning (FL), the critical challenge is to balance local model improvement and global model tuning when the personal and global objectives may not be exactly aligned. Inspired by Bayesian hierarchical models, we develop ActPerFL, a self-aware personalized FL method where each client can automatically balance the training of its local personal model and the global model that implicitly contributes to other clients{'} training. Such a balance is derived from the inter-client and intra-client uncertainty quantification. Consequently, ActPerFL can adapt to the underlying clients{'} heterogeneity with uncertainty-driven local training and model aggregation. With experimental studies on Sent140 and Amazon Alexa audio data, we show that ActPerFL can achieve superior personalization performance compared with the existing counterparts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2022-actperfl">
<titleInfo>
<title>ActPerFL: Active Personalized Federated Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Huili</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Tramel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuang</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anit</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Sahu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Salman</namePart>
<namePart type="family">Avestimehr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Federated Learning for Natural Language Processing (FL4NLP 2022)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bill</namePart>
<namePart type="given">Yuchen</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chaoyang</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chulin</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fatemehsadat</namePart>
<namePart type="family">Mireshghallah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ninareh</namePart>
<namePart type="family">Mehrabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahdi</namePart>
<namePart type="family">Soltanolkotabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the context of personalized federated learning (FL), the critical challenge is to balance local model improvement and global model tuning when the personal and global objectives may not be exactly aligned. Inspired by Bayesian hierarchical models, we develop ActPerFL, a self-aware personalized FL method where each client can automatically balance the training of its local personal model and the global model that implicitly contributes to other clients’ training. Such a balance is derived from the inter-client and intra-client uncertainty quantification. Consequently, ActPerFL can adapt to the underlying clients’ heterogeneity with uncertainty-driven local training and model aggregation. With experimental studies on Sent140 and Amazon Alexa audio data, we show that ActPerFL can achieve superior personalization performance compared with the existing counterparts.</abstract>
<identifier type="citekey">chen-etal-2022-actperfl</identifier>
<identifier type="doi">10.18653/v1/2022.fl4nlp-1.1</identifier>
<location>
<url>https://aclanthology.org/2022.fl4nlp-1.1</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>1</start>
<end>5</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ActPerFL: Active Personalized Federated Learning
%A Chen, Huili
%A Ding, Jie
%A Tramel, Eric
%A Wu, Shuang
%A Sahu, Anit Kumar
%A Avestimehr, Salman
%A Zhang, Tao
%Y Lin, Bill Yuchen
%Y He, Chaoyang
%Y Xie, Chulin
%Y Mireshghallah, Fatemehsadat
%Y Mehrabi, Ninareh
%Y Li, Tian
%Y Soltanolkotabi, Mahdi
%Y Ren, Xiang
%S Proceedings of the First Workshop on Federated Learning for Natural Language Processing (FL4NLP 2022)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F chen-etal-2022-actperfl
%X In the context of personalized federated learning (FL), the critical challenge is to balance local model improvement and global model tuning when the personal and global objectives may not be exactly aligned. Inspired by Bayesian hierarchical models, we develop ActPerFL, a self-aware personalized FL method where each client can automatically balance the training of its local personal model and the global model that implicitly contributes to other clients’ training. Such a balance is derived from the inter-client and intra-client uncertainty quantification. Consequently, ActPerFL can adapt to the underlying clients’ heterogeneity with uncertainty-driven local training and model aggregation. With experimental studies on Sent140 and Amazon Alexa audio data, we show that ActPerFL can achieve superior personalization performance compared with the existing counterparts.
%R 10.18653/v1/2022.fl4nlp-1.1
%U https://aclanthology.org/2022.fl4nlp-1.1
%U https://doi.org/10.18653/v1/2022.fl4nlp-1.1
%P 1-5
Markdown (Informal)
[ActPerFL: Active Personalized Federated Learning](https://aclanthology.org/2022.fl4nlp-1.1) (Chen et al., FL4NLP 2022)
ACL
- Huili Chen, Jie Ding, Eric Tramel, Shuang Wu, Anit Kumar Sahu, Salman Avestimehr, and Tao Zhang. 2022. ActPerFL: Active Personalized Federated Learning. In Proceedings of the First Workshop on Federated Learning for Natural Language Processing (FL4NLP 2022), pages 1–5, Dublin, Ireland. Association for Computational Linguistics.