A Statistical Relational Approach to Learning Distance-based GCNs
This work addresses relational data analysis for researchers and practitioners in machine learning, offering a novel approach that is incremental in its method adaptation.
The paper tackled the problem of learning distance-based Graph Convolutional Networks (GCNs) for relational data by embedding graphs into Euclidean space and constructing a secondary graph based on distances, resulting in superior performance over 12 different models and techniques in empirical evaluations.
We consider the problem of learning distance-based Graph Convolutional Networks (GCNs) for relational data. Specifically, we first embed the original graph into the Euclidean space $\mathbb{R}^m$ using a relational density estimation technique thereby constructing a secondary Euclidean graph. The graph vertices correspond to the target triples and edges denote the Euclidean distances between the target triples. We emphasize the importance of learning the secondary Euclidean graph and the advantages of employing a distance matrix over the typically used adjacency matrix. Our comprehensive empirical evaluation demonstrates the superiority of our approach over $12$ different GCN models, relational embedding techniques and rule learning techniques.