Saved in:
Bibliographic Details
Main Authors: Scott, Jonathan, Zakerinia, Hossein, Lampert, Christoph H.
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2306.05515
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910786296741888
author Scott, Jonathan
Zakerinia, Hossein
Lampert, Christoph H.
author_facet Scott, Jonathan
Zakerinia, Hossein
Lampert, Christoph H.
contents We present PeFLL, a new personalized federated learning algorithm that improves over the state-of-the-art in three aspects: 1) it produces more accurate models, especially in the low-data regime, and not only for clients present during its training phase, but also for any that may emerge in the future; 2) it reduces the amount of on-client computation and client-server communication by providing future clients with ready-to-use personalized models that require no additional finetuning or optimization; 3) it comes with theoretical guarantees that establish generalization from the observed clients to future ones. At the core of PeFLL lies a learning-to-learn approach that jointly trains an embedding network and a hypernetwork. The embedding network is used to represent clients in a latent descriptor space in a way that reflects their similarity to each other. The hypernetwork takes as input such descriptors and outputs the parameters of fully personalized client models. In combination, both networks constitute a learning algorithm that achieves state-of-the-art performance in several personalized federated learning benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2306_05515
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle PeFLL: Personalized Federated Learning by Learning to Learn
Scott, Jonathan
Zakerinia, Hossein
Lampert, Christoph H.
Machine Learning
We present PeFLL, a new personalized federated learning algorithm that improves over the state-of-the-art in three aspects: 1) it produces more accurate models, especially in the low-data regime, and not only for clients present during its training phase, but also for any that may emerge in the future; 2) it reduces the amount of on-client computation and client-server communication by providing future clients with ready-to-use personalized models that require no additional finetuning or optimization; 3) it comes with theoretical guarantees that establish generalization from the observed clients to future ones. At the core of PeFLL lies a learning-to-learn approach that jointly trains an embedding network and a hypernetwork. The embedding network is used to represent clients in a latent descriptor space in a way that reflects their similarity to each other. The hypernetwork takes as input such descriptors and outputs the parameters of fully personalized client models. In combination, both networks constitute a learning algorithm that achieves state-of-the-art performance in several personalized federated learning benchmarks.
title PeFLL: Personalized Federated Learning by Learning to Learn
topic Machine Learning
url https://arxiv.org/abs/2306.05515