Stochastic Unrolled Federated Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Hadou, Samar, NaderiAlizadeh, Navid, Ribeiro, Alejandro
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929235434668032
author Hadou, Samar
NaderiAlizadeh, Navid
Ribeiro, Alejandro
author_facet Hadou, Samar
NaderiAlizadeh, Navid
Ribeiro, Alejandro
contents Algorithm unrolling has emerged as a learning-based optimization paradigm that unfolds truncated iterative algorithms in trainable neural-network optimizers. We introduce Stochastic UnRolled Federated learning (SURF), a method that expands algorithm unrolling to federated learning in order to expedite its convergence. Our proposed method tackles two challenges of this expansion, namely the need to feed whole datasets to the unrolled optimizers to find a descent direction and the decentralized nature of federated learning. We circumvent the former challenge by feeding stochastic mini-batches to each unrolled layer and imposing descent constraints to guarantee its convergence. We address the latter challenge by unfolding the distributed gradient descent (DGD) algorithm in a graph neural network (GNN)-based unrolled architecture, which preserves the decentralized nature of training in federated learning. We theoretically prove that our proposed unrolled optimizer converges to a near-optimal region infinitely often. Through extensive numerical experiments, we also demonstrate the effectiveness of the proposed framework in collaborative training of image classifiers.
format Preprint
id arxiv_https___arxiv_org_abs_2305_15371
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Stochastic Unrolled Federated Learning
Hadou, Samar
NaderiAlizadeh, Navid
Ribeiro, Alejandro
Machine Learning
Signal Processing
Algorithm unrolling has emerged as a learning-based optimization paradigm that unfolds truncated iterative algorithms in trainable neural-network optimizers. We introduce Stochastic UnRolled Federated learning (SURF), a method that expands algorithm unrolling to federated learning in order to expedite its convergence. Our proposed method tackles two challenges of this expansion, namely the need to feed whole datasets to the unrolled optimizers to find a descent direction and the decentralized nature of federated learning. We circumvent the former challenge by feeding stochastic mini-batches to each unrolled layer and imposing descent constraints to guarantee its convergence. We address the latter challenge by unfolding the distributed gradient descent (DGD) algorithm in a graph neural network (GNN)-based unrolled architecture, which preserves the decentralized nature of training in federated learning. We theoretically prove that our proposed unrolled optimizer converges to a near-optimal region infinitely often. Through extensive numerical experiments, we also demonstrate the effectiveness of the proposed framework in collaborative training of image classifiers.
title Stochastic Unrolled Federated Learning
topic Machine Learning
Signal Processing
url https://arxiv.org/abs/2305.15371