Home > Research > Publications & Outputs > Federated χ-armed Bandit with Flexible Personal...

Electronic data

View graph of relations

Federated χ-armed Bandit with Flexible Personalisation

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Forthcoming

Standard

Federated χ-armed Bandit with Flexible Personalisation. / Arabzadeh, A.; Grant, J.A.; Leslie, D.S.
In: Transactions on Machine Learning Research, Vol. 2024, 27.11.2024.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Arabzadeh, A, Grant, JA & Leslie, DS 2024, 'Federated χ-armed Bandit with Flexible Personalisation', Transactions on Machine Learning Research, vol. 2024.

APA

Vancouver

Arabzadeh A, Grant JA, Leslie DS. Federated χ-armed Bandit with Flexible Personalisation. Transactions on Machine Learning Research. 2024 Nov 27;2024.

Author

Arabzadeh, A. ; Grant, J.A. ; Leslie, D.S. / Federated χ-armed Bandit with Flexible Personalisation. In: Transactions on Machine Learning Research. 2024 ; Vol. 2024.

Bibtex

@article{4c189990616a45548a9690e73d503206,
title = "Federated χ-armed Bandit with Flexible Personalisation",
abstract = "This paper introduces a novel approach to personalised federated learning within the X -armed bandit framework, addressing the challenge of optimising both local and global objectives in a highly heterogeneous environment. Our method employs a surrogate objective function that combines individual client preferences with aggregated global knowledge, allowing for a flexible trade-off between personalisation and collective learning. We propose a phasebased elimination algorithm that achieves sublinear regret with logarithmic communication overhead, making it well-suited for federated settings. Theoretical analysis and empirical evaluations demonstrate the effectiveness of our approach compared to existing methods. Potential applications of this work span various domains, including healthcare, smart home devices, and e-commerce, where balancing personalisation with global insights is crucial.",
author = "A. Arabzadeh and J.A. Grant and D.S. Leslie",
year = "2024",
month = nov,
day = "27",
language = "English",
volume = "2024",
journal = "Transactions on Machine Learning Research",

}

RIS

TY - JOUR

T1 - Federated χ-armed Bandit with Flexible Personalisation

AU - Arabzadeh, A.

AU - Grant, J.A.

AU - Leslie, D.S.

PY - 2024/11/27

Y1 - 2024/11/27

N2 - This paper introduces a novel approach to personalised federated learning within the X -armed bandit framework, addressing the challenge of optimising both local and global objectives in a highly heterogeneous environment. Our method employs a surrogate objective function that combines individual client preferences with aggregated global knowledge, allowing for a flexible trade-off between personalisation and collective learning. We propose a phasebased elimination algorithm that achieves sublinear regret with logarithmic communication overhead, making it well-suited for federated settings. Theoretical analysis and empirical evaluations demonstrate the effectiveness of our approach compared to existing methods. Potential applications of this work span various domains, including healthcare, smart home devices, and e-commerce, where balancing personalisation with global insights is crucial.

AB - This paper introduces a novel approach to personalised federated learning within the X -armed bandit framework, addressing the challenge of optimising both local and global objectives in a highly heterogeneous environment. Our method employs a surrogate objective function that combines individual client preferences with aggregated global knowledge, allowing for a flexible trade-off between personalisation and collective learning. We propose a phasebased elimination algorithm that achieves sublinear regret with logarithmic communication overhead, making it well-suited for federated settings. Theoretical analysis and empirical evaluations demonstrate the effectiveness of our approach compared to existing methods. Potential applications of this work span various domains, including healthcare, smart home devices, and e-commerce, where balancing personalisation with global insights is crucial.

M3 - Journal article

VL - 2024

JO - Transactions on Machine Learning Research

JF - Transactions on Machine Learning Research

ER -