Presentation
Graph Neural Networks Automated Design and Deployment on Device-Edge Co-Inference Systems
DescriptionThe key to device-edge co-inference paradigm is to partition models into computation-friendly and computation-intensive parts across device and edge, respectively. However, for Graph Neural Networks (GNNs), partitioning without architecture exploration is ineffective due to various computational-communication overheads of GNN operations over heterogeneous devices. We present GCoDE, the first automatic framework that co-designs the GNN architecture and operation mapping. GCoDE abstracts communication process into explicit operation, fuses architecture search and operations mapping in a joint-optimization space. Also, the performance-awareness approach enables effective evaluation of architecture efficiency. Experiments show GCoDE achieves up to 44.9x speedup and 98.2% energy reduction across various systems.
Event Type
Research Manuscript
TimeTuesday, June 2510:30am - 10:45am PDT
Location3001, 3rd Floor
AI
AI/ML Algorithms