Graph convolutional network (GCN) is a powerful model studied broadly in various graph structural data learning tasks. However, to mitigate the over-smoothing phenomenon, and deal with heterogeneous graph structural data, the design of GCN model remains a crucial issue to be investigated. In this paper, we propose a novel GCN called SStaGCN (Simplified stacking based GCN) by utilizing the ideas of stacking and aggregation, which is an adaptive general framework for tackling heterogeneous graph data. Specifically, we first use the base models of stacking to extract the node features of a graph. Subsequently, aggregation methods such as mean, attention and voting techniques are employed to further enhance the ability of node features extraction. Thereafter, the node features are considered as inputs and fed into vanilla GCN model. Furthermore, theoretical generalization bound analysis of the proposed model is explicitly given. Extensive experiments on $3$ public citation networks and another $3$ heterogeneous tabular data demonstrate the effectiveness and efficiency of the proposed approach over state-of-the-art GCNs. Notably, the proposed SStaGCN can efficiently mitigate the over-smoothing problem of GCN.

翻译：图卷积网络（GCN）是一种强大的模型，在各种图结构数据学习任务中得到了广泛研究。然而，为了缓解过平滑现象并处理异构图结构数据，GCN模型的设计仍是一个有待研究的关键问题。本文通过利用堆叠与聚合的思想，提出了一种名为SStaGCN（基于简化堆叠的GCN）的新型GCN，它是一个用于处理异构图数据的自适应通用框架。具体而言，我们首先使用堆叠的基模型来提取图的节点特征。随后，采用均值、注意力及投票等聚合方法进一步增强节点特征提取能力。此后，将节点特征作为输入馈入原始GCN模型。此外，本文明确给出了所提模型的理论泛化界分析。在$3$个公开引用网络及另外$3$个异构表格数据上进行的大量实验表明，所提方法相较于最先进的GCN具有更高的有效性和效率。值得注意的是，所提SStaGCN能有效缓解GCN的过平滑问题。