A Joint Framework for Inductive Representation Learning and Explainable Reasoning in Knowledge Graphs

Despite their large-scale coverage, existing cross-domain knowledge graphs invariably suffer from inherent incompleteness and sparsity, necessitating link prediction that requires inferring a target entity, given a source entity and a query relation. Recent approaches can broadly be classified into two categories: embedding-based approaches and path-based approaches. In contrast to embedding-based approaches, which operate in an uninterpretable latent semantic vector space of entities and relations, path-based approaches operate in the symbolic space, making the inference process explainable. However, traditionally, these approaches are studied with static snapshots of the knowledge graphs, severely restricting their applicability for dynamic knowledge graphs with newly emerging entities. To overcome this issue, we propose an inductive representation learning framework that is able to learn representations of previously unseen entities. Our method finds reasoning paths between source and target entities, thereby making the link prediction for unseen entities interpretable and providing support evidence for the inferred link.