Inductive Link Prediction for Nodes Having Only Attribute Information

TL;DR

This paper introduces DEAL, a novel model for inductive link prediction in attributed graphs that effectively utilizes attribute information for predicting links involving new nodes without prior structure data.

Contribution

The paper presents DEAL, a new model that combines attribute and structure embeddings with an alignment mechanism, enabling improved inductive link prediction.

Findings

DEAL outperforms existing inductive link prediction methods.

DEAL also surpasses state-of-the-art transductive methods.

The model is versatile for both inductive and transductive tasks.

Abstract

Predicting the link between two nodes is a fundamental problem for graph data analytics. In attributed graphs, both the structure and attribute information can be utilized for link prediction. Most existing studies focus on transductive link prediction where both nodes are already in the graph. However, many real-world applications require inductive prediction for new nodes having only attribute information. It is more challenging since the new nodes do not have structure information and cannot be seen during the model training. To solve this problem, we propose a model called DEAL, which consists of three components: two node embedding encoders and one alignment mechanism. The two encoders aim to output the attribute-oriented node embedding and the structure-oriented node embedding, and the alignment mechanism aligns the two types of embeddings to build the connections between the attributes and links. Our model DEAL is versatile in the sense that it works for both inductive and transductive link prediction. Extensive experiments on several benchmark datasets show that our proposed model significantly outperforms existing inductive link prediction methods, and also outperforms the state-of-the-art methods on transductive link prediction.