Graph neural networks (GNNs) have been widely investigated in the field of semi-supervised graph machine learning. Most methods fail to exploit adequate graph information when labeled data is limited, leading to the problem of oversmoothing. To overcome this issue, we propose the Graph Alignment Neural Network (GANN), a simple and effective graph neural architecture. A unique learning algorithm with three alignment rules is proposed to thoroughly explore hidden information for insufficient labels. Firstly, to better investigate attribute specifics, we suggest the feature alignment rule to align the inner product of both the attribute and embedding matrices. Secondly, to properly utilize the higher-order neighbor information, we propose the cluster center alignment rule, which involves aligning the inner product of the cluster center matrix with the unit matrix. Finally, to get reliable prediction results with few labels, we establish the minimum entropy alignment rule by lining up the prediction probability matrix with its sharpened result. Extensive studies on graph benchmark datasets demonstrate that GANN can achieve considerable benefits in semi-supervised node classification and outperform state-of-the-art competitors.

翻译：图神经网络在半监督图机器学习领域已得到广泛研究。当标注数据有限时，大多数方法未能充分利用图信息，导致过平滑问题。为克服这一难题，我们提出图对齐神经网络（GANN），一种简单而有效的图神经架构。我们提出了一种具有三种对齐规则的独特学习算法，以充分挖掘信息不足标签中的隐藏信息。首先，为更好地探究属性细节，我们提出特征对齐规则，即将属性矩阵与嵌入矩阵的内积进行对齐。其次，为合理利用高阶邻居信息，我们提出聚类中心对齐规则，即对聚类中心矩阵与单位矩阵的内积进行对齐。最后，为在少量标签下获得可靠的预测结果，我们建立最小熵对齐规则，通过将预测概率矩阵与其锐化结果进行对齐来实现。在多个图基准数据集上的广泛研究表明，GANN在半监督节点分类任务中可取得显著优势，并超越当前最先进的竞争者。