FL-GNNs: Robust Network Representation via Feature Learning Guided Graph Neural Networks

Graph Neural Networks (GNNs) have been widely developed and grown rapidly to address representation and learning for attribute graph data $G(A,X)$. However, existing studies on GNNs mainly focus on the message passing on graph $A$ for layer-wise propagation while pay less attention to the robust learning for the input features $X$, which thus make existing GNNs often perform susceptibility w.r.t feature noises and adversarial perturbations in $X$. In this article, we propose a novel Feature Learning guided Graph Neural Networks (FL-GNNs) by incorporating robust feature learning into GNNs. The core of FL-GNNs is trying to recover (or learn) a more clean and optimal feature data $Z$ from input features $X$ that better serves GNNs learning by jointly conducting feature reconstruction and GNNs' learning simultaneously. FL-GNNs is general and can be incorporated into any specific GNN models to enhance their robustness. An efficient algorithm has been derived to optimize FL-GNNs. Experimental results show that FL-GNNs can obviously enhance the robustness of existing GCN and GAT w.r.t feature noises and adversarial perturbations.