Saved in:
Bibliographic Details
Main Authors: Nikoloutsopoulos, Sotirios, Koutsopoulos, Iordanis, Titsias, Michalis K.
Format: Preprint
Published: 2022
Subjects:
Online Access:https://arxiv.org/abs/2202.09848
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912758546563072
author Nikoloutsopoulos, Sotirios
Koutsopoulos, Iordanis
Titsias, Michalis K.
author_facet Nikoloutsopoulos, Sotirios
Koutsopoulos, Iordanis
Titsias, Michalis K.
contents We propose a Stochastic Gradient Descent (SGD)-type algorithm for Personalized Federated Learning which can be particularly attractive for mobile energy-limited regimes due to its low per-client computational cost. The model to be trained includes a set of common weights for all clients, and a set of personalized weights that are specific to each client. At each optimization round, randomly selected clients perform multiple full gradient-descent updates over their client-specific weights towards optimizing the loss function on their own datasets, without updating the common weights. This procedure is energy-efficient since it has low computational cost per client. At the final update of each round, each client computes the joint gradient over both the client-specific and the common weights and returns the gradient of common weights to the server, which allows to perform an exact SGD step over the full set of weights in a distributed manner. For the overall optimization scheme, we rigorously prove convergence, even in non-convex settings such as those encountered when training neural networks, with a rate of $\mathcal{O} \left (\frac{1}{\sqrt{T}} \right )$ with respect to communication rounds $T$. In practice, PFLEGO exhibits substantially lower per-round wall-clock time, used as a proxy for energy. Our theoretical guarantees translate to superior performance in practice against baselines such as FedAvg and FedPer, as evaluated in several multi-class classification datasets, in particular, Omniglot, CIFAR-10, MNIST, Fashion-MNIST, and EMNIST.
format Preprint
id arxiv_https___arxiv_org_abs_2202_09848
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Personalized Federated Learning with Exact Stochastic Gradient Descent
Nikoloutsopoulos, Sotirios
Koutsopoulos, Iordanis
Titsias, Michalis K.
Machine Learning
We propose a Stochastic Gradient Descent (SGD)-type algorithm for Personalized Federated Learning which can be particularly attractive for mobile energy-limited regimes due to its low per-client computational cost. The model to be trained includes a set of common weights for all clients, and a set of personalized weights that are specific to each client. At each optimization round, randomly selected clients perform multiple full gradient-descent updates over their client-specific weights towards optimizing the loss function on their own datasets, without updating the common weights. This procedure is energy-efficient since it has low computational cost per client. At the final update of each round, each client computes the joint gradient over both the client-specific and the common weights and returns the gradient of common weights to the server, which allows to perform an exact SGD step over the full set of weights in a distributed manner. For the overall optimization scheme, we rigorously prove convergence, even in non-convex settings such as those encountered when training neural networks, with a rate of $\mathcal{O} \left (\frac{1}{\sqrt{T}} \right )$ with respect to communication rounds $T$. In practice, PFLEGO exhibits substantially lower per-round wall-clock time, used as a proxy for energy. Our theoretical guarantees translate to superior performance in practice against baselines such as FedAvg and FedPer, as evaluated in several multi-class classification datasets, in particular, Omniglot, CIFAR-10, MNIST, Fashion-MNIST, and EMNIST.
title Personalized Federated Learning with Exact Stochastic Gradient Descent
topic Machine Learning
url https://arxiv.org/abs/2202.09848