Elastic Graph Neural Networks
Elastic Graph Neural Networks
复制标题
DOI：
--
复制
发表时间：
2021-07
期刊：
影响因子：
--
通讯作者：
Xiaorui Liu;W. Jin;Yao Ma;Yaxin Li;Hua Liu;Yiqi Wang;Ming Yan;Jiliang Tang
中科院分区：
文献类型：
--
作者：
Xiaorui Liu;W. Jin;Yao Ma;Yaxin Li;Hua Liu;Yiqi Wang;Ming Yan;Jiliang Tang
虽然许多现有的图神经网络(GNN)已经被证明执行基于$\ELL_2$的图平滑以实现全局平滑，但在本工作中，我们的目标是通过基于$\ELL_1$的图平滑来进一步增强GNN的局部光滑性自适应性。因此，我们引入了一类基于$\ell_1$和$\ell_2$图平滑的弹性GNN(Elastic GNN)。特别地，我们在GNN中提出了一种新颖而通用的消息传递方案。这种消息传递算法不仅有利于反向传播训练，而且在理论收敛的保证下达到了期望的平滑特性。在半监督学习任务上的实验表明，所提出的弹性GNN在基准数据集上具有更好的自适应性，并且对图攻击具有明显的鲁棒性。弹性GNN的实现可在\url{https://github.com/lxiaorui/ElasticGNN}.
While many existing graph neural networks (GNNs) have been proven to perform $\ell_2$-based graph smoothing that enforces smoothness globally, in this work we aim to further enhance the local smoothness adaptivity of GNNs via $\ell_1$-based graph smoothing. As a result, we introduce a family of GNNs (Elastic GNNs) based on $\ell_1$ and $\ell_2$-based graph smoothing. In particular, we propose a novel and general message passing scheme into GNNs. This message passing algorithm is not only friendly to back-propagation training but also achieves the desired smoothing properties with a theoretical convergence guarantee. Experiments on semi-supervised learning tasks demonstrate that the proposed Elastic GNNs obtain better adaptivity on benchmark datasets and are significantly robust to graph adversarial attacks. The implementation of Elastic GNNs is available at \url{https://github.com/lxiaorui/ElasticGNN}.