Graph-MLP: Node Classification without Message Passing in Graph

Abstract

Graph Neural Network (GNN) has been demonstrated its effectiveness in dealing with non-Euclidean structural data. Both spatial-based and spectral-based GNNs are relying on adjacency matrix to guide message passing among neighbors during feature aggregation. Recent works have mainly focused on powerful message passing modules, however, in this paper, we show that none of the message passing modules is necessary. Instead, we propose a pure multilayer-perceptron-based framework, Graph-MLP with the supervision signal leveraging graph structure, which is sufficient for learning discriminative node representation. In model-level, Graph-MLP only includes multi-layer perceptrons, activation function, and layer normalization. In the loss level, we design a neighboring contrastive (NContrast) loss to bridge the gap between GNNs and MLPs by utilizing the adjacency information implicitly. This design allows our model to be lighter and more robust when facing large-scale graph data and corrupted adjacency information. Extensive experiments prove that even without adjacency information in testing phase, our framework can still reach comparable and even superior performance against the state-of-the-art models in the graph node classification task.

arXiv comment11 pages, 6 figures

References in corpus (16)

• Adam: A Method for Stochastic Optimization
• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Gaussian Error Linear Units (GELUs)
• Simplifying Graph Convolutional Networks
• Big Self-Supervised Models are Strong Semi-Supervised Learners
• Gated Graph Sequence Neural Networks
• GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs
• LanczosNet: Multi-Scale Deep Graph Convolutional Networks
• Design Space for Graph Neural Networks
• Self-supervised Learning on Graphs: Deep Insights and New Direction
• Do You Even Need Attention? A Stack of Feed-Forward Layers Does Surprisingly Well on ImageNet
• RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition
• Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning

Cited by in corpus (5)

• Knowledge Graph Contrastive Learning Based on Relation-Symmetrical Structure
• Lifelong Learning on Evolving Graphs Under the Constraints of Imbalanced Classes and New Classes
• Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods
• Open-World Lifelong Graph Learning
• Contributions to Representation Learning with Graph Autoencoders and Applications to Music Recommendation