A heuristic using server learning plus filtering and geometric median aggregation maintains high accuracy in federated learning with over 50% malicious clients and small non-matching server data.
Breakdown points of affine equivariant estimators of multivariate location and covariance matrices
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
-
Enhancing Robustness of Federated Learning via Server Learning
A heuristic using server learning plus filtering and geometric median aggregation maintains high accuracy in federated learning with over 50% malicious clients and small non-matching server data.