SubFLOT uses optimal transport to generate data-aware personalized submodels via server-side pruning and scaling-based adaptive regularization to mitigate parametric divergence in heterogeneous federated learning.
Mobilenetv2: Inverted residuals and linear bottlenecks
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
LoRA fine-tuning delivers better GI disease classification accuracy than full end-to-end fine-tuning while using far fewer parameters.
citing papers explorer
-
SubFLOT: Submodel Extraction for Efficient and Personalized Federated Learning via Optimal Transport
SubFLOT uses optimal transport to generate data-aware personalized submodels via server-side pruning and scaling-based adaptive regularization to mitigate parametric divergence in heterogeneous federated learning.
-
Parameter Efficient Fine-tuning for Domain-specific Gastrointestinal Disease Recognition
LoRA fine-tuning delivers better GI disease classification accuracy than full end-to-end fine-tuning while using far fewer parameters.