Graph classification aims to categorise graphs based on their structure and node attributes. In this work, we propose to tackle this task using tools from graph signal processing by deriving spectral features, which we then use to design two variants of Gaussian process models for graph classification. The first variant uses spectral features based on the distribution of energy of a node feature signal over the spectrum of the graph. We show that even such a simple approach, having no learned parameters, can yield competitive performance compared to strong neural network and graph kernel baselines. A second, more sophisticated variant is designed to capture multi-scale and localised patterns in the graph by learning spectral graph wavelet filters, obtaining improved performance on synthetic and real-world data sets. Finally, we show that both models produce well calibrated uncertainty estimates, enabling reliable decision making based on the model predictions.

翻译：图分类旨在根据图的结构和节点属性对其进行分类。在本工作中，我们利用图信号处理中的工具，通过提取谱特征来应对这一任务，并据此设计了两种用于图分类的高斯过程模型变体。第一种变体使用基于节点特征信号在图谱上能量分布的谱特征。我们证明，即便这种无学习参数的简单方法，也能与强大的神经网络和图核基线方法相媲美，取得具有竞争力的性能。第二种更复杂的变体通过学习谱图小波滤波器来捕捉图中的多尺度与局部模式，在合成数据集和真实数据集上均获得了更优的性能。最后，我们展示了这两种模型均能产生校准良好的不确定性估计，从而基于模型预测实现可靠的决策。