NE-WNA: A Novel Network Embedding Framework Without Neighborhood Aggregation

Abstract

Graph Neural Networks (GNNs) are powerful tools in representation learning for graphs. Most GNNs use the message passing mechanism to obtain a distinguished feature representation. However, due to this message passing mechanism, most existing GNNs are inherently restricted by over-smoothing and poor robustness. Therefore, we propose a simple yet effective N etwork E mbedding framework W ithout N eighborhood A ggregation (NE-WNA). Specifically, NE-WNA removes the neighborhood aggregation operation from the message passing mechanism. It only takes node features as input and then obtains node representations by a simple autoencoder. We also design an enhanced neighboring contrastive (ENContrast) loss to incorporate the graph structure into the node representations. In the representation space, the ENContrast encourages low-order neighbors to be closer to the target node than high-order neighbors. Experimental results show that NE-WNA enjoys high accuracy on the node classification task and high robustness against adversarial attacks.