Graph-MLP: Node Classification without Message Passing in Graph
This work addresses graph node classification for researchers and practitioners by offering a lighter and more robust alternative to traditional GNNs, though it is incremental as it builds on existing MLP and contrastive learning ideas.
The paper tackles the problem of node classification in graphs by proposing Graph-MLP, a framework that eliminates message passing modules and uses only multilayer perceptrons with a neighboring contrastive loss, achieving comparable or superior performance to state-of-the-art models without adjacency information during testing.
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.