An original model for multi-target learning of logical rules for knowledge graph reasoning

TL;DR

This paper introduces a novel multi-target logical rule learning model for knowledge graph reasoning, enhancing interpretability and performance in completing missing facts, validated by experiments on benchmark datasets.

Contribution

The paper presents a new model that fully utilizes training data for multi-target reasoning and introduces two indicators for better evaluation of rule quality.

Findings

Outperforms state-of-the-art methods on five datasets

Demonstrates effectiveness of the proposed indicators

Enhances interpretability and generalization in knowledge graph reasoning

Abstract

Large-scale knowledge graphs provide structured representations of human knowledge. However, as it is impossible to collect all knowledge, knowledge graphs are usually incomplete. Reasoning based on existing facts paves a way to discover missing facts. In this paper, we study the problem of learning logical rules for reasoning on knowledge graphs for completing missing factual triplets. Learning logical rules equips a model with strong interpretability as well as the ability to generalize to similar tasks. We propose a model able to fully use training data which also considers multi-target scenarios. In addition, considering the deficiency in evaluating the performance of models and the quality of mined rules, we further propose two novel indicators to help with the problem. Experimental results empirically demonstrate that our model outperforms state-of-the-art methods on five benchmark datasets. The results also prove the effectiveness of the indicators.