NOSMOG: Learning Noise-robust and Structure-aware MLPs on Graphs

08/22/2022
by   Yijun Tian, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
12/11/2021

A Comparative Study on Robust Graph Neural Networks to Structural Noises

Graph neural networks (GNNs) learn node representations by passing and a...
research
10/17/2021

Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation

Graph Neural Networks (GNNs) have recently become popular for graph mach...
research
05/09/2021

Graph Attention Networks with Positional Embeddings

Graph Neural Networks (GNNs) are deep learning methods which provide the...
research
02/01/2023

Knowledge Distillation on Graphs: A Survey

Graph Neural Networks (GNNs) have attracted tremendous attention by demo...
research
05/07/2023

LSGNN: Towards General Graph Neural Network in Node Classification by Local Similarity

Heterophily has been considered as an issue that hurts the performance o...
research
08/23/2021

Graph Attention Multi-Layer Perceptron

Graph neural networks (GNNs) have recently achieved state-of-the-art per...
research
10/08/2021

Stable Prediction on Graphs with Agnostic Distribution Shift

Graph is a flexible and effective tool to represent complex structures i...

Please sign up or login with your details

Forgot password? Click here to reset