Graph summarization as a preprocessing step is an effective and complementary
technique for scalable graph neural network (GNN) training. In this work, we
propose the Coarsening Via Convolution Matching (CONVMATCH) algorithm and a
highly scalable variant, A-CONVMATCH, for creating summarized graphs that
preserve the output of graph convolution. We evaluate CONVMATCH on six
real-world link prediction and node classification graph datasets, and show it
is efficient and preserves prediction performance while significantly reducing
the graph size. Notably, CONVMATCH achieves up to 95% of the prediction
performance of GNNs on node classification while trained on graphs summarized
down to 1% the size of the original graph. Furthermore, on link prediction
tasks, CONVMATCH consistently outperforms all baselines, achieving up to a 2x
improvement.

通过 CONVMATCH 算法和高度可扩展的变种 A-CONVMATCH，我们提出了一种用于创建保持图卷积输出的图摘要的算法，证明 CONVMATCH 在六个真实的链接预测和节点分类图数据集上是高效的，并且在显著减小图大小的同时保持了预测性能，特别地，在节点分类上，我们在图的摘要大小为原图的 1% 时，CONVMATCH 达到了 GNN 节点分类性能的 95%，并且在链接预测任务上，CONVMATCH 始终优于所有基准，达到了最多 2 倍的改进。