Joint placement and routing for fixed-partition DNN inference over multi-hop edge networks is addressed with an alternating optimization framework that shows split flexibility matters most in IoT-edge-cloud settings and congestion awareness helps as load increases.
Dnn partitioning for cooperative inference in edge intelligence: Modeling, solutions, toolchains
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Design Insights into Partition Placement and Routing for DNN Inference in Multi-Hop Edge Networks
Joint placement and routing for fixed-partition DNN inference over multi-hop edge networks is addressed with an alternating optimization framework that shows split flexibility matters most in IoT-edge-cloud settings and congestion awareness helps as load increases.