Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction

by   Jinheon Baek, et al.

Many practical graph problems, such as knowledge graph construction and drug-to-drug interaction, require to handle multi-relational graphs. However, handling real-world multi-label graphs with Graph Neural Networks (GNNs) is often challenging due to their evolving nature, where new entities (nodes) can emerge over time. Moreover, newly emerged entities often have few links, which makes the learning even more difficult. Motivated by this challenge, we introduce a realistic problem of few-shot out-of-graph link prediction, where we not only predict the links between the seen and unseen nodes as in a conventional out-of-knowledge link prediction but also between the unseen nodes, with only few edges per node. We tackle this problem with a novel transductive meta-learning framework which we refer to as Graph Extrapolation Networks (GEN). GEN meta-learns both the node embedding network for inductive inference (seen-to-unseen) and the link prediction network for transductive inference (unseen-to-unseen). For transductive link prediction, we further propose a stochastic embedding layer to model uncertainty in the link prediction between unseen entities. We validate our model on multiple benchmark datasets for knowledge graph link prediction and drug-to-drug interaction prediction. The results show that our model significantly outperforms relevant baselines for out-of-graph link prediction tasks.



There are no comments yet.


page 1

page 2

page 3

page 4


Few-shot link prediction via graph neural networks for Covid-19 drug-repurposing

Predicting interactions among heterogenous graph structured data has num...

Inductive Link Prediction for Nodes Having Only Attribute Information

Predicting the link between two nodes is a fundamental problem for graph...

Drug Similarity and Link Prediction Using Graph Embeddings on Medical Knowledge Graphs

The paper utilizes the graph embeddings generated for entities of a larg...

Improving Inductive Link Prediction Using Hyper-Relational Facts

For many years, link prediction on knowledge graphs (KGs) has been a pur...

GENN: Predicting Correlated Drug-drug Interactions with Graph Energy Neural Networks

Gaining more comprehensive knowledge about drug-drug interactions (DDIs)...

Heterogeneous Graph based Deep Learning for Biomedical Network Link Prediction

Multi-scale biomedical knowledge networks are expanding with emerging ex...

Inter-domain Multi-relational Link Prediction

Multi-relational graph is a ubiquitous and important data structure, all...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.