Algorithms recover Wasserstein distance matrices from few entries via matrix completion and Nyström sampling, with MDS stability proof and stable OrganCMNIST classification at 10% column budget.
Medmnist v2-a large-scale lightweight benchmark for 2d and 3d biomedical image classification
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
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
-
Recovering Wasserstein Distance Matrices from Few Measurements
Algorithms recover Wasserstein distance matrices from few entries via matrix completion and Nyström sampling, with MDS stability proof and stable OrganCMNIST classification at 10% column budget.
-
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.