Inductive Relation Prediction from Relational Paths and Context with Hierarchical Transformers

TL;DR

This paper introduces REPORT, a hierarchical transformer-based method for inductive relation prediction in knowledge graphs that effectively captures relational paths and entity context, enabling better generalization to unseen entities.

Contribution

REPORT is a novel hierarchical transformer framework that leverages relation semantics and entity context for inductive reasoning in knowledge graphs, outperforming existing methods.

Findings

REPORT outperforms all baselines on multiple datasets

The method is fully inductive, generalizing to unseen entities

REPORT provides interpretable contribution analysis

Abstract

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.