EdgeFD uses a KMeans-based client-side filter to improve federated distillation accuracy close to IID levels on non-IID data distributions for resource-constrained edge devices.
Distillation-based semi-supervised federated learning for communication-efficient collaborative training with non-iid private data
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Federated Distillation on Edge Devices: Efficient Client-Side Filtering for Non-IID Data
EdgeFD uses a KMeans-based client-side filter to improve federated distillation accuracy close to IID levels on non-IID data distributions for resource-constrained edge devices.