Privacy loss in DPWFL converges to a constant rather than diverging, with convergence guarantees for non-convex losses including gradient clipping and an explicit privacy-utility trade-off.
Communication-efficient learning of deep networks from decentralized data
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
GraphPL combines GNNs with patchwork learning to integrate all observed modalities for unsupervised imputation, achieving SOTA results on benchmarks and enabling disease prediction on real EHR data.
FedKPer improves the generalization-personalization trade-off in medical federated learning via local knowledge personalization and selective aggregation that emphasizes reliable updates.
citing papers explorer
-
When Differential Privacy Meets Wireless Federated Learning: An Improved Analysis for Privacy and Convergence
Privacy loss in DPWFL converges to a constant rather than diverging, with convergence guarantees for non-convex losses including gradient clipping and an explicit privacy-utility trade-off.
-
GraphPL: Leveraging GNN for Efficient and Robust Modalities Imputation in Patchwork Learning
GraphPL combines GNNs with patchwork learning to integrate all observed modalities for unsupervised imputation, achieving SOTA results on benchmarks and enabling disease prediction on real EHR data.
-
FedKPer: Tackling Generalization and Personalization in Medical Federated Learning via Knowledge Personalization
FedKPer improves the generalization-personalization trade-off in medical federated learning via local knowledge personalization and selective aggregation that emphasizes reliable updates.