Stratify improves federated learning on non-IID data by balancing label exposure through a stratified label schedule and label-aware client selection.
The cost of training machine learning models over distributed data sources,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Stratify: Rethinking Federated Learning for Non-IID Data through Balanced Sampling
Stratify improves federated learning on non-IID data by balancing label exposure through a stratified label schedule and label-aware client selection.