Graph neural networks (GNNs) have emerged as a popular strategy for handling non-Euclidean data due to their state-of-the-art performance. However, most of the current GNN model designs mainly focus on task accuracy, lacking in considering hardware resources limitation and real-time requirements of edge application scenarios. Comprehensive profiling of typical GNN models indicates that their execution characteristics are significantly affected across different computing platforms, which demands hardware awareness for efficient GNN designs. In this work, HGNAS is proposed as the first Hardware-aware Graph Neural Architecture Search framework targeting resource constraint edge devices. By decoupling the GNN paradigm, HGNAS constructs a fine-grained design space and leverages an efficient multi-stage search strategy to explore optimal architectures within a few GPU hours. Moreover, HGNAS achieves hardware awareness during the GNN architecture design by leveraging a hardware performance predictor, which could balance the GNN model accuracy and efficiency corresponding to the characteristics of targeted devices. Experimental results show that HGNAS can achieve about $10.6\times$ speedup and $88.2\%$ peak memory reduction with a negligible accuracy loss compared to DGCNN on various edge devices, including Nvidia RTX3080, Jetson TX2, Intel i7-8700K and Raspberry Pi 3B+.

翻译：图神经网络（GNN）因具有最先进的性能，已成为处理非欧几里得数据的流行策略。然而，当前大多数GNN模型设计主要关注任务精度，缺乏考虑边缘应用场景的硬件资源限制和实时性要求。对典型GNN模型的全面性能分析表明，其执行特性在不同计算平台上存在显著差异，这要求在设计高效GNN时具备硬件感知能力。本文提出HGNAS，这是首个面向资源受限边缘设备的硬件感知图神经架构搜索框架。通过解耦GNN范式，HGNAS构建了细粒度的设计空间，并利用高效的多阶段搜索策略，在数GPU小时内探索出最优架构。此外，HGNAS通过引入硬件性能预测器实现GNN架构设计过程中的硬件感知能力，该预测器可针对目标设备特性平衡GNN模型的精度与效率。实验结果表明，与DGCNN相比，在Nvidia RTX3080、Jetson TX2、Intel i7-8700K和Raspberry Pi 3B+等多种边缘设备上，HGNAS可实现约10.6倍的加速和88.2%的峰值内存减少，同时精度损失可忽略不计。