Scalability of Graph Neural Networks (GNNs) remains a significant challenge. To tackle this, methods like coarsening, condensation, and computation trees are used to train on a smaller graph, resulting in faster computation. Nonetheless, prior research has not adequately addressed the computational costs during the inference phase. This paper presents a novel approach to improve the scalability of GNNs by reducing computational burden during the inference phase using graph coarsening. We demonstrate two different methods -- Extra Nodes and Cluster Nodes. Our study extends the application of graph coarsening for graph-level tasks, including graph classification and graph regression. We conduct extensive experiments on multiple benchmark datasets to evaluate the performance of our approach. Our results show that the proposed method achieves orders of magnitude improvements in single-node inference time compared to traditional approaches. Furthermore, it significantly reduces memory consumption for node and graph classification and regression tasks, enabling efficient training and inference on low-resource devices where conventional methods are impractical. Notably, these computational advantages are achieved while maintaining competitive performance relative to baseline models.

翻译：图神经网络（GNN）的可扩展性仍是一项重大挑战。为此，现有方法采用图粗化、图凝聚及计算树等技术在缩小的图上进行训练，从而提升计算效率。然而，先前研究尚未充分解决推理阶段的计算成本问题。本文提出一种创新方法，通过图粗化技术降低推理阶段的计算负担，从而提升GNN的可扩展性。我们展示了两种不同的方法——额外节点法与聚类节点法。本研究将图粗化技术拓展至图级任务（包括图分类与图回归）的应用场景。我们在多个基准数据集上开展了大量实验以评估所提方法的性能。结果表明，与传统方法相比，本方法可实现单节点推理时间的数量级提升。此外，该方法能显著降低节点分类、图分类及图回归任务的内存消耗，使得传统方法难以适用的低资源设备也能高效进行训练与推理。值得注意的是，这些计算优势是在保持与基准模型竞争性性能的前提下实现的。