A heterogeneous graph attention Q-network is introduced for AISC deployment that reduces completion time while improving load balance and energy use in dynamic UMEC networks.
Enhancing Resilience in Distributed ML Inference Pipelines for Edge Computing,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
The paper surveys energy efficiency strategies for Agentic AI inference by proposing a new accounting framework and taxonomy that spans model simplification, computation control, input optimization, and cross-layer co-design with wireless networks.
GraphSAGE achieves 94.2% detection rate, 0.955 AUC, and 1.4s response time for cyberattacks on drone systems in an emulation study, outperforming GCN and GAT.
citing papers explorer
-
AISC deployment in dynamic UAV-assisted MEC network: a reinforcement learning method based on heterogeneous graph attention neural network
A heterogeneous graph attention Q-network is introduced for AISC deployment that reduces completion time while improving load balance and energy use in dynamic UMEC networks.
-
Networking-Aware Energy Efficiency in Agentic AI Inference: A Survey
The paper surveys energy efficiency strategies for Agentic AI inference by proposing a new accounting framework and taxonomy that spans model simplification, computation control, input optimization, and cross-layer co-design with wireless networks.
-
Graph neural networks at war: integrating cybersecurity and drone intelligence in the Israeli-Iranian conflict
GraphSAGE achieves 94.2% detection rate, 0.955 AUC, and 1.4s response time for cyberattacks on drone systems in an emulation study, outperforming GCN and GAT.