论文标题
EEGNN：带有贝叶斯非参数图模型的边缘增强图形神经网络
EEGNN: Edge Enhanced Graph Neural Network with a Bayesian Nonparametric Graph Model
论文作者
论文摘要
训练深图神经网络（GNNS）构成了一项具有挑战性的任务，因为GNN的性能可能会遭受隐藏的消息层的数量。文献集中在{过度平滑}和{降低}的建议上，以解释深度GNN的性能恶化。在本文中，我们为这种恶化的性能现象提出了一个新的解释，即{miS simplification}，也就是说，通过防止自行宽图和强迫边缘未加权来简化图形。我们表明，这种简化可以降低通过消息层捕获图形的结构信息的潜力。鉴于此，我们提出了一个新的框架，Edge增强了图形神经网络（EEGNN）。 EEGNN使用从提出的Dirichlet混合泊松图模型（DMPGM）（贝叶斯非参数模型）中提取的结构信息，以提高各种深度消息串起的GNN的性能。我们为DMPGM提出了马尔可夫链蒙特卡洛推理框架。不同数据集的实验表明，与基线相比，我们的方法实现了可观的性能。
Training deep graph neural networks (GNNs) poses a challenging task, as the performance of GNNs may suffer from the number of hidden message-passing layers. The literature has focused on the proposals of {over-smoothing} and {under-reaching} to explain the performance deterioration of deep GNNs. In this paper, we propose a new explanation for such deteriorated performance phenomenon, {mis-simplification}, that is, mistakenly simplifying graphs by preventing self-loops and forcing edges to be unweighted. We show that such simplifying can reduce the potential of message-passing layers to capture the structural information of graphs. In view of this, we propose a new framework, edge enhanced graph neural network (EEGNN). EEGNN uses the structural information extracted from the proposed Dirichlet mixture Poisson graph model (DMPGM), a Bayesian nonparametric model for graphs, to improve the performance of various deep message-passing GNNs. We propose a Markov chain Monte Carlo inference framework for DMPGM. Experiments over different datasets show that our method achieves considerable performance increase compared to baselines.
