</> Code with Papers by Syntology

Papers › Personalized Federated Learning using Hypernetworks

Personalized Federated Learning using Hypernetworks

8 Mar 2021arXiv:2103.04628archive 2025-07-28

Aviv Shamsian, Aviv Navon, Ethan Fetaya, Gal Chechik

Personalized federated learning is tasked with training machine learning models for multiple clients, each with its own data distribution. The goal is to train personalized models in a collaborative way while accounting for data disparities across clients and reducing communication costs. We propose a novel approach to this problem using hypernetworks, termed pFedHN for personalized Federated HyperNetworks. In this approach, a central hypernetwork model is trained to generate a set of models, one model for each client. This architecture provides effective parameter sharing across clients, while maintaining the capacity to generate unique and diverse personal models. Furthermore, since hypernetwork parameters are never transmitted, this approach decouples the communication cost from the trainable model size. We test pFedHN empirically in several personalized federated learning challenges and find that it outperforms previous methods. Finally, since hypernetworks share information across clients we show that pFedHN can generalize better to new clients whose distributions differ from any client observed during training.

PaperPDFCode

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

Code

AvivSham/pFedHN officialmentioned in papermentioned on GitHubpytorch report
KarhouTam/FL-bench mentioned on GitHubpytorchGPL-3.0 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 LearningPersonalized Federated Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Personalized Federated Learning CIFAR-10 pFedHN-PC ACC@1-100Clients 88.09 #1 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-10 pFedHN-PC ACC@1-10Clients 92.47 #1 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-10 pFedHN-PC ACC@1-500Clients 83.2 #1 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-10 pFedHN-PC ACC@1-50Clients 90.08 #1 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-10 pFedHN ACC@1-100Clients 87.97 #2 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-10 pFedHN ACC@1-10Clients 90.83 #2 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-10 pFedHN ACC@1-50Clients 88.38 #2 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-100 pFedHN-PC ACC@1-100Clients 52.40 #4 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-100 pFedHN-PC ACC@1-10Clients 68.15 #4 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-100 pFedHN-PC ACC@1-500 34.1 #4 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-100 pFedHN-PC ACC@1-50Clients 60.17 #4 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-100 pFedHN ACC@1-100Clients 53.24 #5 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-100 pFedHN ACC@1-10Clients 65.74 #5 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-100 pFedHN ACC@1-50Clients 59.46 #5 of 7 Archive leaderboard report
Personalized Federated Learning Omniglot pFedHN-PC ACC@1-50Clients 81.89 #1 of 2 Archive leaderboard report
Personalized Federated Learning Omniglot pFedHN ACC@1-50Clients 72.03 #2 of 2 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

HyperNetwork

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