Graph neural networks (GNNs) have been widely used under semi-supervised settings. Prior studies have mainly focused on finding appropriate graph filters (e.g., aggregation schemes) to generalize well for both homophilic and heterophilic graphs. Even though these approaches are essential and effective, they still suffer from the sparsity in initial node features inherent in the bag-of-words representation. Common in semi-supervised learning where the training samples often fail to cover the entire dimensions of graph filters (hyperplanes), this can precipitate over-fitting of specific dimensions in the first projection matrix. To deal with this problem, we suggest a simple and novel strategy; create additional space by flipping the initial features and hyperplane simultaneously. Training in both the original and in the flip space can provide precise updates of learnable parameters. To the best of our knowledge, this is the first attempt that effectively moderates the overfitting problem in GNN. Extensive experiments on real-world datasets demonstrate that the proposed technique improves the node classification accuracy up to 40.2 %

翻译：图神经网络（GNN）已在半监督场景下得到广泛应用。现有研究主要关注寻找合适的图滤波器（如聚合机制）以在同类和异类图中实现良好泛化。尽管这些方法至关重要且有效，但它们仍受限于词袋表示中初始节点特征固有的稀疏性。在半监督学习中，训练样本通常无法覆盖图滤波器（超平面）的全部维度，这可能导致首个投影矩阵中特定维度的过拟合。为解决该问题，我们提出一种简单而新颖的策略：通过同时翻转初始特征与超平面来创建额外的空间。在原始空间和翻转空间中进行训练，可为可学习参数提供精确的更新。据我们所知，这是首次有效缓解GNN过拟合问题的研究。在真实世界数据集上的大量实验表明，所提技术可将节点分类准确率提升高达40.2%。