AIC-GNN: Adversarial information completion for graph neural networks

Graph neural networks (GNNs) have attracted extensive attention due to their demonstrated powerful performance in various graph mining tasks. The implicit assumption of GNNs being able to work is that all nodes have adequate information for meaningful aggregation. However, this is not easy to satisfy because the degrees of a real-world graph commonly follow the power-law distribution, where most nodes belong to low-degree nodes with limited neighborhoods. In this paper, we argue that to make GNNs better handle the low-degree node representation learning is the key to solving the above problem and propose a pluggable framework named Adversarial Information Completion Graph Neural Networks (AIC-GNN). It introduces a novel Graph Information Generator to fit adaptively the node missing information distribution. Then, the Graph Embedding Discriminator distinguishes between the node embeddings with the ideal information and the node embeddings after information completion. The representational capacity of the model is enhanced by adversarial training between the Generator and Discriminator. Meanwhile, the dual node embedding alignment mechanisms are employed to guide the high quality of predicted information. Extensive experiments demonstrate that AIC-GNN outperforms state-of-the-art methods on four real-world graphs.(c) 2022 Elsevier Inc. All rights reserved.

Automated summary

This paper proposes a pluggable framework called Adversarial Information Completion Graph Neural Networks (AIC-GNN) to address the problem of low-degree node representation learning. A novel Graph Information Generator is introduced to adaptively fit the node missing information distribution, and adversarial training is used to enhance the representational capacity of the model. Extensive experiments demonstrate the superior performance of AIC-GNN compared to state-of-the-art methods on four real-world graphs.