A loss-trajectory-based clustering method for federated learning, plus a Wasserstein-adjusted cluster metric, reports improved personalization on heterogeneous data.
Title resolution pending
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
-
Interaction-Aware Gaussian Weighting for Clustered Federated Learning
A loss-trajectory-based clustering method for federated learning, plus a Wasserstein-adjusted cluster metric, reports improved personalization on heterogeneous data.