Personalized Federated Learning using Hypernetworks

8 Mar 2021 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... (read more)

PDF Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
Personalized Federated Learning CIFAR-10 pFedHN-PC ACC@1-10Clients 92.47 # 1
ACC@1-50Clients 90.08 # 2
ACC@1-100Clients 88.09 # 1
Personalized Federated Learning CIFAR-10 pFedHN ACC@1-10Clients 90.83 # 2
ACC@1-50Clients 88.38 # 1
ACC@1-100Clients 87.97 # 2
Personalized Federated Learning CIFAR-100 pFedHN-PC ACC@1-10Clients 68.15 # 1
ACC@1-50Clients 60.17 # 1
ACC@1-100Clients 52.40 # 2
Personalized Federated Learning CIFAR-100 pFedHN ACC@1-10Clients 65.74 # 2
ACC@1-50Clients 59.46 # 2
ACC@1-100Clients 53.24 # 1
Personalized Federated Learning Omniglot pFedHN-PC ACC@1-50Clients 81.89 # 1
Personalized Federated Learning Omniglot pFedHN ACC@1-50Clients 72.03 # 2

Methods used in the Paper


METHOD TYPE
HyperNetwork
Feedforward Networks