论文标题
从光谱图汇报到大型图卷积网络
From Spectral Graph Convolutions to Large Scale Graph Convolutional Networks
论文作者
论文摘要
图形卷积网络（GCN）已被证明是一个有力的概念，在过去几年中，已成功应用于许多领域的各种任务。在这项工作中，我们研究了为GCN定义铺平道路的理论，包括经典图理论的相关部分。我们还讨论并在实验上证明了GCN的关键特性和局限性，例如由图形边缘引入的样品统计依赖性引起的，这导致完整梯度的估计值偏置。我们讨论的另一个限制是Minibatch采样对模型性能的负面影响。结果，在参数更新期间，在整个数据集上计算梯度，从而破坏了对大图的可扩展性。为此，我们研究了替代方法，这些方法允许在每次迭代中仅采样一部分数据的同时，可以安全地学习良好的参数。我们重现了Kipf等人的工作中报告的结果。并提出一个灵感签名的实现，这是一种无抽样的minibatch方法。最终，我们比较了基准数据集上的两个实现，证明它们在半监督节点分类任务的预测准确性方面是可比的。
Graph Convolutional Networks (GCNs) have been shown to be a powerful concept that has been successfully applied to a large variety of tasks across many domains over the past years. In this work we study the theory that paved the way to the definition of GCN, including related parts of classical graph theory. We also discuss and experimentally demonstrate key properties and limitations of GCNs such as those caused by the statistical dependency of samples, introduced by the edges of the graph, which causes the estimates of the full gradient to be biased. Another limitation we discuss is the negative impact of minibatch sampling on the model performance. As a consequence, during parameter update, gradients are computed on the whole dataset, undermining scalability to large graphs. To account for this, we research alternative methods which allow to safely learn good parameters while sampling only a subset of data per iteration. We reproduce the results reported in the work of Kipf et al. and propose an implementation inspired to SIGN, which is a sampling-free minibatch method. Eventually we compare the two implementations on a benchmark dataset, proving that they are comparable in terms of prediction accuracy for the task of semi-supervised node classification.
