A joint graph-learning and signal-restoration aggregation step, solved as a difference-of-convex program, improves federated learning accuracy under noisy client updates.
We first formulate a graph-based aggregation in the global model update as a DC optimization problem and then solve it using PDCA
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
-
Joint Graph Estimation and Signal Restoration for Robust Federated Learning
A joint graph-learning and signal-restoration aggregation step, solved as a difference-of-convex program, improves federated learning accuracy under noisy client updates.