arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2205.05348cs.LGcs.AI
收藏

基于NDGGNET-A节点独立门的图神经网络

NDGGNET-A Node Independent Gate based Graph Neural Networks

JD Group(京东集团)

Ye Tang, Xuesong Yang, Xinrui Liu, Xiwei Zhao, Zhangang Lin, Changping Peng

摘要:

图神经网络(Graph Neural Network,GNNs)是一种结构化数据的网络结构,在链接预测、节点分类、图分类等领域得到了广泛的应用,并取得了令人满意的效果。通常,对于给定图中的某个节点,传统的GNN层可以看作是一跳邻居的聚合,因此,一组堆叠层能够在多跳内获取和更新节点状态。对于稀疏连接的节点,很难通过单个GNN层获得足够的信息,因为不仅只有很少的节点直接连接到它们,而且不能传播高阶邻居信息。然而,随着层数的增加,GNN模型容易对密集连接的节点进行过平滑,从而导致精度下降。为了解决这个问题,在这篇论文中,我们定义了一个新的框架,允许正常的GNN模型,以容纳更多的层。具体地说,基于节点度的门被用来动态地调整层的权重,试图提高信息聚合能力和减少过度平滑的概率。实验结果表明,我们提出的模型可以有效地增加模型的深度,并在多个数据集上表现良好。

英文摘要:

Graph Neural Networks (GNNs) is an architecture for structural data, and has been adopted in a mass of tasks and achieved fabulous results, such as link prediction, node classification, graph classification and so on. Generally, for a certain node in a given graph, a traditional GNN layer can be regarded as an aggregation from one-hop neighbors, thus a set of stacked layers are able to fetch and update node status within multi-hops. For nodes with sparse connectivity, it is difficult to obtain enough information through a single GNN layer as not only there are only few nodes directly connected to them but also can not propagate the high-order neighbor information. However, as the number of layer increases, the GNN model is prone to over-smooth for nodes with the dense connectivity, which resulting in the decrease of accuracy. To tackle this issue, in this thesis, we define a novel framework that allows the normal GNN model to accommodate more layers. Specifically, a node-degree based gate is employed to adjust weight of layers dynamically, that try to enhance the information aggregation ability and reduce the probability of over-smoothing. Experimental results show that our proposed model can effectively increase the model depth and perform well on several datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑