pFedLIA clusters federated learning clients using a cheap 'lazy influence' score, and on CIFAR10/100 and FashionMNIST it matches a perfect-clustering oracle while improving on existing personalized FL baselines by up to 17 percentage points.
Personalized and private peer-to-peer machine learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Lazy But Effective: Collaborative Personalized Federated Learning with Heterogeneous Data
pFedLIA clusters federated learning clients using a cheap 'lazy influence' score, and on CIFAR10/100 and FashionMNIST it matches a perfect-clustering oracle while improving on existing personalized FL baselines by up to 17 percentage points.