Bandwidth Slicing to Boost Federated Learning in Edge Computing
arXiv:1911.07615v13 citations
Originality Synthesis-oriented
AI Analysis
This addresses communication bottlenecks for federated learning in edge computing, but appears incremental as it applies an existing concept (bandwidth slicing) to a specific domain.
The paper tackled the problem of communication delay in federated learning for edge computing by introducing bandwidth slicing, resulting in significant improvements in training efficiency and good learning accuracy.
Bandwidth slicing is introduced to support federated learning in edge computing to assure low communication delay for training traffic. Results reveal that bandwidth slicing significantly improves training efficiency while achieving good learning accuracy.