论文标题
合成图生成至基准图学习
Synthetic Graph Generation to Benchmark Graph Learning
论文作者
论文摘要
图形学习算法已经在许多图形分析任务（例如节点分类，链接预测和聚类）上达到了最先进的性能。但是，很难跟踪该领域的新兴进步。原因之一是由于在实践中使用的数据集数量很少，用于基准图形学习算法的性能。这种令人震惊的小样本量（〜10）只允许对问题的科学见解有限。 在这项工作中，我们旨在解决这种缺陷。我们建议在受控方案中生成合成图，并研究图形学习算法的行为。我们开发了功能齐全的合成图生成器，可深入检查不同模型。我们认为，合成图一代可以彻底研究算法，并提供比在三个引用数据集上过度拟合的更多见解。在案例研究中，我们展示了我们的框架如何提供对无监督和监督的图形神经网络模型的见解。
Graph learning algorithms have attained state-of-the-art performance on many graph analysis tasks such as node classification, link prediction, and clustering. It has, however, become hard to track the field's burgeoning progress. One reason is due to the very small number of datasets used in practice to benchmark the performance of graph learning algorithms. This shockingly small sample size (~10) allows for only limited scientific insight into the problem. In this work, we aim to address this deficiency. We propose to generate synthetic graphs, and study the behaviour of graph learning algorithms in a controlled scenario. We develop a fully-featured synthetic graph generator that allows deep inspection of different models. We argue that synthetic graph generations allows for thorough investigation of algorithms and provides more insights than overfitting on three citation datasets. In the case study, we show how our framework provides insight into unsupervised and supervised graph neural network models.
