EMD-CFL clusters federated learning clients in one shot by comparing Earth Mover's distances between randomly projected embedding distributions, matching oracle clustering on several benchmarks.
We use Python Optimal Transport 0.9.5 [Flamary et al., 2021] for the EMD calculations
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
-
Clustered Federated Learning via Embedding Distributions
EMD-CFL clusters federated learning clients in one shot by comparing Earth Mover's distances between randomly projected embedding distributions, matching oracle clustering on several benchmarks.