CRAFT derives a closed-form solution for conflict-resolved aggregation in federated learning via geometric constraints and projection, with theoretical support for common descent and empirical gains on heterogeneous data.
Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, and Blaise Aguera y Arcas
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CRAFT: Conflict-Resolved Aggregation for Federated Training
CRAFT derives a closed-form solution for conflict-resolved aggregation in federated learning via geometric constraints and projection, with theoretical support for common descent and empirical gains on heterogeneous data.