PracMHBench evaluates eight model-heterogeneous federated learning algorithms under practical edge device constraints and finds that depth-level heterogeneity wins under compute/communication limits while memory limits change the ranking.
A public domain dataset for human activity recognition using smartphones
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
PracMHBench: Re-evaluating Model-Heterogeneous Federated Learning Based on Practical Edge Device Constraints
PracMHBench evaluates eight model-heterogeneous federated learning algorithms under practical edge device constraints and finds that depth-level heterogeneity wins under compute/communication limits while memory limits change the ranking.