</> Code with Papers by Syntology

Papers › Personalized Federated Learning with Gaussian Processes

Personalized Federated Learning with Gaussian Processes

29 Jun 2021NeurIPS 2021 12arXiv:2106.15482archive 2025-07-28

Idan Achituve, Aviv Shamsian, Aviv Navon, Gal Chechik, Ethan Fetaya

Federated learning aims to learn a global model that performs well on client devices with limited cross-client communication. Personalized federated learning (PFL) further extends this setup to handle data heterogeneity between clients by learning personalized models. A key challenge in this setting is to learn effectively across clients even though each client has unique data that is often limited in size. Here we present pFedGP, a solution to PFL that is based on Gaussian processes (GPs) with deep kernel learning. GPs are highly expressive models that work well in the low data regime due to their Bayesian nature. However, applying GPs to PFL raises multiple challenges. Mainly, GPs performance depends heavily on access to a good kernel function, and learning a kernel requires a large training set. Therefore, we propose learning a shared kernel function across all clients, parameterized by a neural network, with a personal GP classifier for each client. We further extend pFedGP to include inducing points using two novel methods, the first helps to improve generalization in the low data regime and the second reduces the computational cost. We derive a PAC-Bayes generalization bound on novel clients and empirically show that it gives non-vacuous guarantees. Extensive experiments on standard PFL benchmarks with CIFAR-10, CIFAR-100, and CINIC-10, and on a new setup of learning under input noise show that pFedGP achieves well-calibrated predictions while significantly outperforming baseline methods, reaching up to 21% in accuracy gain.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

IdanAchituve/pFedGP officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Federated LearningGaussian ProcessesPersonalized Federated Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Personalized Federated Learning CIFAR-10 pFedGP-IP-compute ACC@1-100Clients 88.8 #5 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-10 pFedGP-IP-compute ACC@1-500Clients 86.8 #5 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-10 pFedGP-IP-compute ACC@1-50Clients 89.9 #5 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-10 pFedGP ACC@1-100Clients 88.8 #6 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-10 pFedGP ACC@1-500Clients 87.6 #6 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-10 pFedGP ACC@1-50Clients 89.2 #6 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-10 pFedGP-IP-data ACC@1-100Clients 87.4 #7 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-10 pFedGP-IP-data ACC@1-500Clients 86.9 #7 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-10 pFedGP-IP-data ACC@1-50Clients 88.6 #7 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-100 pFedGP-IP-data ACC@1-100Clients 58.5 #1 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-100 pFedGP-IP-data ACC@1-500 55.7 #1 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-100 pFedGP-IP-data ACC@1-50Clients 60.2 #1 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-100 pFedGP ACC@1-100Clients 61.3 #2 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-100 pFedGP ACC@1-500 50.6 #2 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-100 pFedGP ACC@1-50Clients 63.3 #2 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-100 pFedGP-IP-compute ACC@1-100Clients 59.8 #3 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-100 pFedGP-IP-compute ACC@1-500 49.2 #3 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-100 pFedGP-IP-compute ACC@1-50Clients 61.2 #3 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

GPS

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections