Learning to Model Graph Structural Information on MLPs via Graph Structure Self-Contrasting
- 30 September 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 36 (7) , 12772-12783
Abstract
Recent years have witnessed great success in handling graph-related tasks with graph neural networks (GNNs). However, most existing GNNs are based on message passing to perform feature aggregation and transformation, where the structural information is explicitly involved in the forward propagation by coupling with node features through graph convolution at each layer. As a result, subtle feature noise or structure perturbation may cause severe error propagation, resulting in extremely poor robustness. In this article, we rethink the roles played by graph structural information in graph data training and identify that message passing is not the only path to modeling structural information. Inspired by this, we propose a simple but effective graph structure self-contrasting (GSSC) framework that learns graph structural information without message passing. The proposed framework is based purely on multilayer perceptrons (MLPs), where the structural information is only implicitly incorporated as prior knowledge to guide the computation of supervision signals, substituting the explicit message propagation as in GNNs. Specifically, it first applies structural sparsification (STR-Sparse) to remove potentially uninformative or noisy edges in the neighborhood, and then performs structural self-contrasting (STR-Contrast) in the sparsified neighborhood to learn robust node representations. Finally, STR-Sparse and self-contrasting are formulated as a bilevel optimization problem and solved in a unified framework. Extensive experiments have qualitatively and quantitatively demonstrated that the GSSC framework can produce truly encouraging performance with better generalization and robustness than other leading competitors. Codes are publicly available at: https://github.com/LirongWu/GSSC.Keywords
All Related Versions
Funding Information
- National Science and Technology Major Project of China (2022ZD0115101)
- National Natural Science Foundation of China (U21A20427)
- Center of Synthetic Biology and Integrated Bioengineering of Westlake University (WU2022A009)
This publication has 33 references indexed in Scilit:
- Learning to Augment Graph Structure for both Homophily and Heterophily Graphs2023
- Graph Self-Supervised Learning: A SurveyIEEE Transactions on Knowledge and Data Engineering, 2022
- Graph Vulnerability and Robustness: A SurveyIEEE Transactions on Knowledge and Data Engineering, 2022
- Self-Supervised Learning on Graphs: Contrastive, Generative, or PredictiveIEEE Transactions on Knowledge and Data Engineering, 2021
- Graph-Revised Convolutional Network2021
- Graph neural networks: A review of methods and applicationsAI Open, 2020
- Graph Adversarial Training: Dynamically Regularizing Based on Graph StructureIEEE Transactions on Knowledge and Data Engineering, 2019
- Learning Graph Embedding With Adversarial Training MethodsIEEE Transactions on Cybernetics, 2019
- Semi-Supervised Learning With Graph Learning-Convolutional Networks2019
- Deep Inductive Graph Representation LearningIEEE Transactions on Knowledge and Data Engineering, 2018