BitGNN: 在 GPU 上释放二值图神经网络的性能潜能（英文版）

英文标题：BitGNN: Unleashing the Performance Potential of Binary Graph Neural Networks on GPUs中文摘要：本研究提出了一种二进制图神经网络的高效推理后端的重新设计，旨在充分地发挥加速器硬件性能潜力；在实际图形中，使用 GCNs、GraphSAGE 和 GraphSAINT 的结果表明，使用相同的精度，所提出的技术比最先进的二进制 GNN 实现快 8-22 倍。英文摘要：Recent studies have shown that Binary Graph Neural Networks (GNNs) arepromising for saving computations of GNNs through binarized tensors. Priorwork, however, mainly focused on algorithm designs or training techniques,leaving it open to how to materialize the performance