SOURCE-LINKED INTELLIGENCE

Privacy-Aligned Personalized Federated Learning with Compact Adaptation and Variable-Length Gaussian Communication

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Record-level differential privacy exposes a structural misalignment in personalized federated learning when client-specific variation is low-dimensional while training repeatedly releases high-dimensional updates. In this paper, we address this misalignment by releasing a private client context once and confining repeated adaptation to a fixed coefficient space. Beyond dimensionality reduction, the factorized generator induces an adaptive optimization geometry that reshapes noisy updates, and controlled ablations show that most of its private-training gain is retained by radial evolution. To f

Read original source ↗ Open in workspace

recordType

paper

region

Global