Learning on Attribute-Missing Graphs

TL;DR

This paper introduces SAT, a novel GNN designed for graphs with missing node attributes, leveraging distribution matching to improve link prediction and attribute completion, outperforming existing methods on real datasets.

Contribution

The paper proposes a new GNN model, SAT, that effectively handles attribute-missing graphs by joint distribution modeling of structure and attributes.

Findings

SAT outperforms existing methods on real-world datasets.

SAT effectively performs link prediction and node attribute completion.

The model demonstrates robustness across diverse datasets.

Abstract

Graphs with complete node attributes have been widely explored recently. While in practice, there is a graph where attributes of only partial nodes could be available and those of the others might be entirely missing. This attribute-missing graph is related to numerous real-world applications and there are limited studies investigating the corresponding learning problems. Existing graph learning methods including the popular GNN cannot provide satisfied learning performance since they are not specified for attribute-missing graphs. Thereby, designing a new GNN for these graphs is a burning issue to the graph learning community. In this paper, we make a shared-latent space assumption on graphs and develop a novel distribution matching based GNN called structure-attribute transformer (SAT) for attribute-missing graphs. SAT leverages structures and attributes in a decoupled scheme and achieves the joint distribution modeling of structures and attributes by distribution matching techniques. It could not only perform the link prediction task but also the newly introduced node attribute completion task. Furthermore, practical measures are introduced to quantify the performance of node attribute completion. Extensive experiments on seven real-world datasets indicate SAT shows better performance than other methods on both link prediction and node attribute completion tasks. Codes and data are available online: https://github.com/xuChenSJTU/SAT-master-online