Learning on Attribute-Missing Graphs

by   Xu Chen, et al.

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


page 11

page 13

page 14

page 15

page 17


Node Attribute Generation on Graphs

Graph structured data provide two-fold information: graph structures and...

Fair Attribute Completion on Graph with Missing Attributes

Tackling unfairness in graph learning models is a challenging task, as t...

Node Attribute Completion in Knowledge Graphs with Multi-Relational Propagation

The existing literature on knowledge graph completion mostly focuses on ...

AutoAC: Towards Automated Attribute Completion for Heterogeneous Graph Neural Network

Many real-world data can be modeled as heterogeneous graphs that contain...

Discovering Representative Attribute-stars via Minimum Description Length

Graphs are a popular data type found in many domains. Numerous technique...

Enhance Ambiguous Community Structure via Multi-strategy Community Related Link Prediction Method with Evolutionary Process

Most real-world networks suffer from incompleteness or incorrectness, wh...

KGNN: Distributed Framework for Graph Neural Knowledge Representation

Knowledge representation learning has been commonly adopted to incorpora...

Please sign up or login with your details

Forgot password? Click here to reset