Graph-MLP: Node Classification without Message Passing in Graph

by   Yang Hu, et al.

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.



There are no comments yet.


page 9


Generalization and Representational Limits of Graph Neural Networks

We address two fundamental questions about graph neural networks (GNNs)....

Distilling Self-Knowledge From Contrastive Links to Classify Graph Nodes Without Passing Messages

Nowadays, Graph Neural Networks (GNNs) following the Message Passing par...

Learning Parametrised Graph Shift Operators

In many domains data is currently represented as graphs and therefore, t...

Learning Human-Object Interactions by Graph Parsing Neural Networks

This paper addresses the task of detecting and recognizing human-object ...

Graph-in-Graph (GiG): Learning interpretable latent graphs in non-Euclidean domain for biological and healthcare applications

Graphs are a powerful tool for representing and analyzing unstructured, ...

Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach

We target open-world feature extrapolation problem where the feature spa...

Bermuda Triangles: GNNs Fail to Detect Simple Topological Structures

Most graph neural network architectures work by message-passing node vec...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.