Graph Neural Networks Automated Design and Deployment on Device-Edge Co-Inference Systems

arXiv:2404.05605v1 Announce Type: new
Abstract: The key to device-edge co-inference paradigm is to partition models into computation-friendly and computation-intensive parts across the device and the edge, respectively. However, for Graph Neural Networks (GNNs), we find that simply partitioning without altering their structures can hardly achieve the full potential of the co-inference paradigm due to various computational-communication overheads of GNN operations over heterogeneous devices. We present GCoDE, the first automatic framework for GNN that innovatively Co-designs the architecture search and the …

abstract arxiv automated computation cs.ai cs.lg deployment design edge gnns graph graph neural networks however inference key networks neural networks paradigm partitioning systems the edge the key type