Abstract—

For prediction tasks using tabular data, it is possible to extract additional information about the target variable by examining the relationships between the objects. Specifically, if it is possible to receive agraph in which the objects are represented as vertices and the relationships are expressed as edges, then it is likely that the graph structure contains valuable information. Recent research has indicated that jointly training graph neural networks and gradient boostings on this type of data can increase the accuracy of predictions. This article proposes new methods for learning on tabular data that incorporates a graph structure, in an attempt to combine modern multilayer techniques for processing tabular data and graph neural networks. In addition, we discuss ways to mitigate the computational complexity of the proposed models and conduct experiments in both inductive and transductive settings. Our findings demonstrate tha the proposed approaches provide comparable quality to modern methods.

中文翻译：

---

实现 GNN 在表格数据高维多层表示上的高效学习

摘要-

对于使用表格数据的预测任务，可以通过检查对象之间的关系来提取有关目标变量的附加信息。具体地，如果可以接收其中对象被表示为顶点并且关系被表示为边的图，则该图结构很可能包含有价值的信息。最近的研究表明，对此类数据联合训练图神经网络和梯度提升可以提高预测的准确性。本文提出了结合图结构的表格数据学习的新方法，试图将处理表格数据的现代多层技术与图神经网络相结合。此外，我们讨论了减轻所提出模型的计算复杂性的方法，并在归纳和传导设置中进行实验。我们的研究结果表明，所提出的方法提供了与现代方法相当的质量。