论文标题
NOSMOG:在图表上学习噪声和结构感知的MLP
NOSMOG: Learning Noise-robust and Structure-aware MLPs on Graphs
论文作者
论文摘要
尽管图神经网络(GNN)已经证明了它们在处理非欧国人结构数据方面的功效,但由于多跳数据依赖性施加的可伸缩性约束,因此很难将它们部署在实际应用中。现有方法试图通过使用训练有素的GNN的标签训练多层感知器(MLP)来解决此可扩展性问题。即使可以显着改善MLP的性能,但两个问题仍能阻止MLP的表现优于GNN,并在实践中使用:图形结构信息的无知和对节点特征噪声的敏感性。在本文中,我们建议在图(NOSMOG)上学习噪声稳定结构感知的MLP,以克服挑战。具体而言,我们首先将节点内容与位置特征相辅相成,以帮助MLP捕获图形结构信息。然后,我们设计了一种新颖的表示相似性蒸馏策略,以将结构节点相似性注入MLP。最后,我们介绍了对抗性功能的增强,以确保稳定的学习能力噪声,并进一步提高性能。广泛的实验表明,NOSMOG在七个数据集的转导和归纳环境中均优于GNN和最先进的方法,同时保持竞争性推理效率。代码可在https://github.com/meettyj/nosmog上找到。
While Graph Neural Networks (GNNs) have demonstrated their efficacy in dealing with non-Euclidean structural data, they are difficult to be deployed in real applications due to the scalability constraint imposed by multi-hop data dependency. Existing methods attempt to address this scalability issue by training multi-layer perceptrons (MLPs) exclusively on node content features using labels derived from trained GNNs. Even though the performance of MLPs can be significantly improved, two issues prevent MLPs from outperforming GNNs and being used in practice: the ignorance of graph structural information and the sensitivity to node feature noises. In this paper, we propose to learn NOise-robust Structure-aware MLPs On Graphs (NOSMOG) to overcome the challenges. Specifically, we first complement node content with position features to help MLPs capture graph structural information. We then design a novel representational similarity distillation strategy to inject structural node similarities into MLPs. Finally, we introduce the adversarial feature augmentation to ensure stable learning against feature noises and further improve performance. Extensive experiments demonstrate that NOSMOG outperforms GNNs and the state-of-the-art method in both transductive and inductive settings across seven datasets, while maintaining a competitive inference efficiency. Codes are available at https://github.com/meettyj/NOSMOG.