Align as Ideal: Cross-Modal Alignment Binding for Federated Medical Vision-Language Pre-training

no code implementations • 5 Apr 2024 • Zitao Shuai, Liyue Shen

Specifically, to reduce distortions on global-aggregated features while learning diverse semantics from client datasets during local training, we propose to bind the cross-model aligned representation space learned by local models with an unbiased one via guidance-based regularization.

Federated Learning Representation Learning