Hardware-aware GNN NAS paper is accepted by DAC 2023!

👏 Paper title: Hardware-Aware Graph Neural Network Automated Design for Edge Computing Platforms. We explore hardware-aware GNN architecture design for edge devices, leveraging “predicting GNNs with GNNs” to efficiently estimate candidate architecture performance during NAS. By integrating device heterogeneity analysis into exploration, our method achieves significant improvements in both accuracy and efficiency. [related project]