Collaborative and Efficient Personalization with Mixtures of Adaptors

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Almansoori, Abdulla Jasem, Horváth, Samuel, Takáč, Martin
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909530926874624
author Almansoori, Abdulla Jasem
Horváth, Samuel
Takáč, Martin
author_facet Almansoori, Abdulla Jasem
Horváth, Samuel
Takáč, Martin
contents Heterogenous data is prevalent in real-world federated learning. We propose a parameter-efficient framework, Federated Low-Rank Adaptive Learning (FLoRAL), that allows clients to personalize in groups by mixing between low-rank adaptors, where the mixtures are client-specific. FLoRAL is a model parameterization that casts personalized federated learning as a multi-task learning problem, with weight sharing as an implicit regularizer. It is memory-efficient, as the personalized parameters (i.e., base model + adaptors) are all federated. Our results show that FLoRAL can generalize better than a mixture of full models when data are scarce. It can also consistently personalize better than models with a locally tuned adaptor per client. This demonstrates the benefits of "federated personalization" and its robustness against overfitting. We derive the convergence rates and show theoretically that FLoRAL can lead to better variance reduction of the base model's gradients.
format Preprint
id arxiv_https___arxiv_org_abs_2410_03497
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Collaborative and Efficient Personalization with Mixtures of Adaptors
Almansoori, Abdulla Jasem
Horváth, Samuel
Takáč, Martin
Machine Learning
Heterogenous data is prevalent in real-world federated learning. We propose a parameter-efficient framework, Federated Low-Rank Adaptive Learning (FLoRAL), that allows clients to personalize in groups by mixing between low-rank adaptors, where the mixtures are client-specific. FLoRAL is a model parameterization that casts personalized federated learning as a multi-task learning problem, with weight sharing as an implicit regularizer. It is memory-efficient, as the personalized parameters (i.e., base model + adaptors) are all federated. Our results show that FLoRAL can generalize better than a mixture of full models when data are scarce. It can also consistently personalize better than models with a locally tuned adaptor per client. This demonstrates the benefits of "federated personalization" and its robustness against overfitting. We derive the convergence rates and show theoretically that FLoRAL can lead to better variance reduction of the base model's gradients.
title Collaborative and Efficient Personalization with Mixtures of Adaptors
topic Machine Learning
url https://arxiv.org/abs/2410.03497