While there exists a wide variety of graph neural networks (GNN) for node classification, only a minority of them adopt mechanisms that effectively target noise propagation during the message-passing procedure. Additionally, a very important challenge that significantly affects graph neural networks is the issue of scalability which limits their application to larger graphs. In this paper we propose our method named NODE-SELECT: an efficient graph neural network that uses subsetting layers which only allow the best sharing-fitting nodes to propagate their information. By having a selection mechanism within each layer which we stack in parallel, our proposed method NODE-SELECT is able to both reduce the amount noise propagated and adapt the restrictive sharing concept observed in real world graphs. Our NODE-SELECT significantly outperformed existing GNN frameworks in noise experiments and matched state-of-the art results in experiments without noise over different benchmark datasets.
翻译:虽然有各种各样的图象神经网络(GNN)用于节点分类,但只有少数这类网络采用有效针对信息传递程序期间噪音传播的机制。此外,对图形神经网络有重大影响的一个非常重要的挑战是可缩放性问题,这一问题限制了它们应用到更大的图形。在本文中,我们提出了我们称为NODE-SELECT的方法:一个高效图形神经网络,它使用分立层,只能允许最佳的共享节点来传播信息。通过在我们平行堆放的每层中有一个选择机制,我们拟议的方法NODE-SELECT既能够减少所传播的噪音数量,又能够调整现实世界图中观察到的限制性共享概念。我们的模型-SELECT在噪声实验中大大超越了现有的GNNF框架,并在没有不同基准数据集的噪音的实验中与最新艺术结果相匹配。