SLIDE enables simultaneous layer-by-layer model downloading and inference to maximize task throughput in multi-user wireless systems through joint optimization of provisioning, spectrum, and computing resources.
Sense4FL: Vehicular crowdsensing enhanced federated learning for autonomous driving
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.NI 2verdicts
UNVERDICTED 2representative citing papers
TrimCaching introduces parameter-sharing edge caching for AI models, formulates it as a submodular maximization problem with submodular constraints, provides approximation algorithms for special and general cases, and shows improved cache hit ratios in simulations.
citing papers explorer
-
SLIDE: Simultaneous Model Downloading and Inference at the Wireless Network Edge
SLIDE enables simultaneous layer-by-layer model downloading and inference to maximize task throughput in multi-user wireless systems through joint optimization of provisioning, spectrum, and computing resources.
-
TrimCaching: Parameter-sharing Edge Caching for AI Model Downloading
TrimCaching introduces parameter-sharing edge caching for AI models, formulates it as a submodular maximization problem with submodular constraints, provides approximation algorithms for special and general cases, and shows improved cache hit ratios in simulations.