Inductive Relation Prediction from Relational Paths and Context with Hierarchical Transformers
This addresses the limitation of transductive methods in knowledge graph completion for scenarios with unseen entities, though it is an incremental advance over prior inductive approaches.
The paper tackles the problem of inductive relation prediction on knowledge graphs, where existing methods fail to generalize to new entities, and proposes REPORT, a hierarchical transformer framework that aggregates relational paths and context, achieving consistent performance improvements over baselines on fully-inductive datasets.
Relation prediction on knowledge graphs (KGs) is a key research topic. Dominant embedding-based methods mainly focus on the transductive setting and lack the inductive ability to generalize to new entities for inference. Existing methods for inductive reasoning mostly mine the connections between entities, i.e., relational paths, without considering the nature of head and tail entities contained in the relational context. This paper proposes a novel method that captures both connections between entities and the intrinsic nature of entities, by simultaneously aggregating RElational Paths and cOntext with a unified hieRarchical Transformer framework, namely REPORT. REPORT relies solely on relation semantics and can naturally generalize to the fully-inductive setting, where KGs for training and inference have no common entities. In the experiments, REPORT performs consistently better than all baselines on almost all the eight version subsets of two fully-inductive datasets. Moreover. REPORT is interpretable by providing each element's contribution to the prediction results.