SStaGCN: Simplified stacking based graph convolutional networks

TL;DR

SStaGCN is a novel, simplified stacking-based graph convolutional network designed to effectively handle heterogeneous graph data and mitigate over-smoothing, with proven efficiency and effectiveness through extensive experiments.

Contribution

The paper introduces SStaGCN, a new framework combining stacking and aggregation techniques to improve GCN performance on heterogeneous data and reduce over-smoothing.

Findings

Outperforms state-of-the-art GCNs on citation networks and heterogeneous tabular data.

Effectively mitigates over-smoothing in GCNs.

Provides theoretical generalization bounds for the model.

Abstract

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.