Focal Interest
Focal Interest

Graph partition

  1. LPS-GNN scales graph learning to 100-billion-edge graphs
    LPS-GNN enables efficient graph neural network processing on 100 billion-edge graphs using single GPUs, achieving 13.8% improvements in user acquisition tasks through novel graph partitioning.
  2. BenchPCNP provides labeled printed circuit netlist graph data
    BenchPCNP: A labeled printed circuit netlist graph dataset for partitioning benchmarking, constructed from 50 production-verified circuits with 54 distinct module labels following IPC-2612 standards.