NL-SME uses a learnable quadratic Bezier curve, a control point, and per-parameter scaling to reconstruct private images from aggregated multi-step FedAvg updates, matching update directions far more closely than the linear SME baseline.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Trajectory-Aware Information Matching for Multi-Step Gradient Inversion in Federated Learning
NL-SME uses a learnable quadratic Bezier curve, a control point, and per-parameter scaling to reconstruct private images from aggregated multi-step FedAvg updates, matching update directions far more closely than the linear SME baseline.