MTF-Grasp, a two-tier federated learning method that seeds low-data robots with models pre-trained by high-quality clients, reports up to 8% higher grasp accuracy than vanilla FedAvg under data quantity skew.
Fed- erated learning: Strategies for improving communication efficiency,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
MTF-Grasp: A Multi-tier Federated Learning Approach for Robotic Grasping
MTF-Grasp, a two-tier federated learning method that seeds low-data robots with models pre-trained by high-quality clients, reports up to 8% higher grasp accuracy than vanilla FedAvg under data quantity skew.