Combining Inductive and Deductive Reasoning for Query Answering over Incomplete Knowledge Graphs

TL;DR

This paper explores integrating ontologies with embedding-based query answering over incomplete Knowledge Graphs, combining inductive and deductive reasoning to improve answer accuracy significantly.

Contribution

It introduces new strategies for embedding models to incorporate ontologies, including data augmentation and loss function adaptation, and provides novel benchmarks for evaluation.

Findings

Up to 55% improvement in HITS@3 for combined reasoning tasks

Effective ontology-driven data augmentation techniques

Enhanced embedding models with ontology axioms improve reasoning accuracy

Abstract

Current methods for embedding-based query answering over incomplete Knowledge Graphs (KGs) only focus on inductive reasoning, i.e., predicting answers by learning patterns from the data, and lack the complementary ability to do deductive reasoning, which requires the application of domain knowledge to infer further information. To address this shortcoming, we investigate the problem of incorporating ontologies into embedding-based query answering models by defining the task of embedding-based ontology-mediated query answering. We propose various integration strategies into prominent representatives of embedding models that involve (1) different ontology-driven data augmentation techniques and (2) adaptation of the loss function to enforce the ontology axioms. We design novel benchmarks for the considered task based on the LUBM and the NELL KGs and evaluate our methods on them. The achieved improvements in the setting that requires both inductive and deductive reasoning are from 20% to 55% in HITS@3.