Graph-MLP: Node Classification without Message Passing in Graph

TL;DR

Graph-MLP introduces a node classification method that eliminates message passing by using a pure MLP framework combined with a novel contrastive loss, achieving competitive results without relying on adjacency during testing.

Contribution

This work demonstrates that message passing modules are unnecessary for GNNs, proposing a simple MLP-based framework with a new contrastive loss leveraging graph structure.

Findings

Achieves comparable or superior performance to state-of-the-art GNNs.

More robust and lightweight, especially on large-scale and corrupted graphs.

Effective without adjacency information during testing.

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.