Link prediction is a task to estimate the probability of links between nodes in a graph.

( Image credit: Inductive Representation Learning on Large Graphs )

Application domains that require considering relationships among objects which have real-valued attributes are becoming even more important.

In this paper, we study the effect of adding residual connections to shallow and deep graph variational and vanilla autoencoders.

Unsupervised attributed graph representation learning is challenging since both structural and feature information are required to be represented in the latent space.

Ranked #1 on Node Clustering on Cora

GRAPH EMBEDDING GRAPH REPRESENTATION LEARNING LINK PREDICTION NODE CLUSTERING

However, they mainly focus on link prediction on binary relational data, where facts are usually represented as triples in the form of (head entity, relation, tail entity).

Knowledge graphs link entities through relations to provide a structured representation of real world facts.

Ranked #8 on Link Prediction on FB15k-237

However, we find in experiments that many paths given by these models are actually unreasonable, while little works have been done on interpretability evaluation for them.

To address this issue, a novel meta-path-based HIN representation learning framework named mSHINE is designed to simultaneously learn multiple node representations for different meta-paths.

We evaluate DARLING through link prediction for treatments and medicines, on a medical KG constructed from EMR data, and illustrate its superior performance compared to existing KG embedding models.

Biomedical knowledge graphs permit an integrative computational approach to reasoning about biological systems.

We show that the expressive models significantly outperform simple scalable baselines, indicating an opportunity for dedicated efforts to further improve graph ML at scale.

Ranked #1 on Node Classification on MAG240M-LSC

GRAPH LEARNING GRAPH REGRESSION KNOWLEDGE GRAPHS LINK PREDICTION NODE CLASSIFICATION