Proximal visual prompt tuning rectifies non-IID client features so analytic least-squares aggregation yields strong one-shot federated classifiers with zero server training cost.
Deepafl: Deep analytic federated learning,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
FedRAN achieves up to 4.8 pp higher accuracy in federated continual learning while using 30-122× less per-client communication by transmitting truncated-SVD summaries of random-feature Gram matrices and performing closed-form ridge classification after two-level QR-SVD merging.
citing papers explorer
-
FedOPAL: One-Shot Federated Learning via Analytic Visual Prompt Tuning
Proximal visual prompt tuning rectifies non-IID client features so analytic least-squares aggregation yields strong one-shot federated classifiers with zero server training cost.
-
Accurate and Resource-Efficient Federated Continual Learning
FedRAN achieves up to 4.8 pp higher accuracy in federated continual learning while using 30-122× less per-client communication by transmitting truncated-SVD summaries of random-feature Gram matrices and performing closed-form ridge classification after two-level QR-SVD merging.