Theoretical Rule-based Knowledge Graph Reasoning by Connectivity Dependency Discovery

TL;DR

This paper introduces a fundamental theory for rule-based reasoning in knowledge graphs that captures connectivity dependencies through multiple rule types, enabling precise interpretation of triples and achieving state-of-the-art results.

Contribution

The paper presents a novel theoretical framework for rule-based knowledge graph reasoning that considers new rule types and implements it in the RuleDict model.

Findings

RuleDict achieves state-of-the-art performance on a benchmark knowledge graph completion task.

The theory provides precise interpretations for unknown triples.

Multiple new rule types are considered for the first time in knowledge graph reasoning.

Abstract

Discovering precise and interpretable rules from knowledge graphs is regarded as an essential challenge, which can improve the performances of many downstream tasks and even provide new ways to approach some Natural Language Processing research topics. In this paper, we present a fundamental theory for rule-based knowledge graph reasoning, based on which the connectivity dependencies in the graph are captured via multiple rule types. It is the first time for some of these rule types in a knowledge graph to be considered. Based on these rule types, our theory can provide precise interpretations to unknown triples. Then, we implement our theory by what we call the RuleDict model. Results show that our RuleDict model not only provides precise rules to interpret new triples, but also achieves state-of-the-art performances on one benchmark knowledge graph completion task, and is competitive on other tasks.