NOSMOG: Learning Noise-robust and Structure-aware MLPs on Graphs
This work addresses the practical deployment challenges of GNNs in real-world applications by improving MLPs for graph data, representing an incremental advancement in graph learning methods.
The paper tackles the scalability and noise sensitivity issues of Graph Neural Networks (GNNs) by proposing NOSMOG, a method that enhances multi-layer perceptrons (MLPs) with structural awareness and noise robustness, achieving superior performance over GNNs and state-of-the-art methods across seven datasets.
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.