Training Graph Neural Networks by Graphon Estimation
Training Graph Neural Networks by Graphon Estimation
复制标题
DOI：
10.1109/bigdata52589.2021.9671996
复制
发表时间：
2021-09
期刊：
影响因子：
--
通讯作者：
Ziqing Hu-;Yihao Fang-;Lizhen Lin
中科院分区：
文献类型：
--
作者：
Ziqing Hu-;Yihao Fang-;Lizhen Lin
在这项工作中，我们建议通过从底层网络数据获得的图形估计进行重采样来训练图神经网络。更具体地说，首先获得底层网络的图形或链路概率矩阵，从中将重新采样新网络并在每一层的训练过程期间使用该新网络。由于重采样带来的不确定性，它有助于缓解图神经网络(GNN)模型中众所周知的过平滑问题。我们的框架是通用的，计算效率高，概念简单。我们方法的另一个吸引人的特点是，它在训练过程中需要最少的额外调整。大量的数值结果表明，我们的方法与其他超平滑减少GNN训练方法相比具有竞争力，并且在许多情况下优于其他方法。
In this work, we propose to train a graph neural network via resampling from a graphon estimate obtained from the underlying network data. More specifically, the graphon or the link probability matrix of the underlying network is first obtained from which a new network will be resampled and used during the training process at each layer. Due to the uncertainty induced from the resampling, it helps mitigate the well-known issue of over-smoothing in a graph neural network (GNN) model. Our framework is general, computationally efficient, and conceptually simple. Another appealing feature of our method is that it requires minimal additional tuning during the training process. Extensive numerical results show that our approach is competitive with and in many cases outperform the other over-smoothing reducing GNN training methods.