使用图汇总缩放R-GCN训练
Scaling R-GCN Training with Graph Summarization
摘要：
关系图卷积网络（R-GCN）的训练是一项记忆密集型任务。在训练真实世界的图时，需要存储的梯度信息量对于大多数GPU上可用的内存量来说往往太大。在这项工作中，我们尝试使用图形摘要技术来压缩图形，从而减少所需的内存量。在图摘要上训练R-GCN后，我们将权重转移回原始图并尝试对其进行推理。我们在AIFB，MUTAG和AM数据集上获得了合理的结果。我们的实验表明，在图摘要上训练可以产生与原始图上训练相当或更高的准确性。此外，如果我们花时间计算公式中的摘要，我们观察到使用图摘要方法获得的较小图表示减少了计算开销。然而，还需要进一步的实验来评估额外的图形摘要模型，以及我们的发现是否也适用于非常大的图形。
英文摘要：
Training of Relational Graph Convolutional Networks (R-GCN) is a memory intense task. The amount of gradient information that needs to be stored during training for real-world graphs is often too large for the amount of memory available on most GPUs. In this work, we experiment with the use of graph summarization techniques to compress the graph and hence reduce the amount of memory needed. After training the R-GCN on the graph summary, we transfer the weights back to the original graph and attempt to perform inference on it. We obtain reasonable results on the AIFB, MUTAG and AM datasets. Our experiments show that training on the graph summary can yield a comparable or higher accuracy to training on the original graphs.Furthermore, if we take the time to compute the summary out of the equation, we observe that the smaller graph representations obtained with graph summarization methods reduces the computational overhead. However, further experiments are needed to evaluate additional graph summary models and whether our findings also holds true for very large graphs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
