History-Aware and Dynamic Client Contribution in Federated Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Ghosh, Bishwamittra, Basu, Debabrota, Huazhu, Fu, Yuan, Wang, Kanagavelu, Renuga, Peng, Jiang Jin, Yong, Liu, Rick, Goh Siow Mong, Qingsong, Wei
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915458165243904
author Ghosh, Bishwamittra
Basu, Debabrota
Huazhu, Fu
Yuan, Wang
Kanagavelu, Renuga
Peng, Jiang Jin
Yong, Liu
Rick, Goh Siow Mong
Qingsong, Wei
author_facet Ghosh, Bishwamittra
Basu, Debabrota
Huazhu, Fu
Yuan, Wang
Kanagavelu, Renuga
Peng, Jiang Jin
Yong, Liu
Rick, Goh Siow Mong
Qingsong, Wei
contents Federated Learning (FL) is a collaborative machine learning (ML) approach, where multiple clients participate in training an ML model without exposing their private data. Fair and accurate assessment of client contributions facilitates incentive allocation in FL and encourages diverse clients to participate in a unified model training. Existing methods for contribution assessment adopts a co-operative game-theoretic concept, called Shapley value, but under restricted assumptions, e.g., all clients' participating in all epochs or at least in one epoch of FL. We propose a history-aware client contribution assessment framework, called FLContrib, where client-participation is dynamic, i.e., a subset of clients participates in each epoch. The theoretical underpinning of FLContrib is based on the Markovian training process of FL. Under this setting, we directly apply the linearity property of Shapley value and compute a historical timeline of client contributions. Considering the possibility of a limited computational budget, we propose a two-sided fairness criteria to schedule Shapley value computation in a subset of epochs. Empirically, FLContrib is efficient and consistently accurate in estimating contribution across multiple utility functions. As a practical application, we apply FLContrib to detect dishonest clients in FL based on historical Shaplee values.
format Preprint
id arxiv_https___arxiv_org_abs_2403_07151
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle History-Aware and Dynamic Client Contribution in Federated Learning
Ghosh, Bishwamittra
Basu, Debabrota
Huazhu, Fu
Yuan, Wang
Kanagavelu, Renuga
Peng, Jiang Jin
Yong, Liu
Rick, Goh Siow Mong
Qingsong, Wei
Machine Learning
Artificial Intelligence
Cryptography and Security
Federated Learning (FL) is a collaborative machine learning (ML) approach, where multiple clients participate in training an ML model without exposing their private data. Fair and accurate assessment of client contributions facilitates incentive allocation in FL and encourages diverse clients to participate in a unified model training. Existing methods for contribution assessment adopts a co-operative game-theoretic concept, called Shapley value, but under restricted assumptions, e.g., all clients' participating in all epochs or at least in one epoch of FL. We propose a history-aware client contribution assessment framework, called FLContrib, where client-participation is dynamic, i.e., a subset of clients participates in each epoch. The theoretical underpinning of FLContrib is based on the Markovian training process of FL. Under this setting, we directly apply the linearity property of Shapley value and compute a historical timeline of client contributions. Considering the possibility of a limited computational budget, we propose a two-sided fairness criteria to schedule Shapley value computation in a subset of epochs. Empirically, FLContrib is efficient and consistently accurate in estimating contribution across multiple utility functions. As a practical application, we apply FLContrib to detect dishonest clients in FL based on historical Shaplee values.
title History-Aware and Dynamic Client Contribution in Federated Learning
topic Machine Learning
Artificial Intelligence
Cryptography and Security
url https://arxiv.org/abs/2403.07151