Extending Complex Logical Queries on Uncertain Knowledge Graphs

TL;DR

This paper introduces a neural symbolic method for answering complex logical queries on uncertain knowledge graphs, effectively handling uncertainty and incomplete data while avoiding cascading errors and outperforming existing approaches.

Contribution

It presents a novel neural symbolic framework that incorporates forward inference and backward calibration to improve reasoning on uncertain, large-scale knowledge graphs.

Findings

Backward calibration outperforms extended query embedding methods.

The proposed method avoids catastrophic cascading errors.

Complexity remains comparable to state-of-the-art symbolic methods.

Abstract

The study of machine learning-based logical query answering enables reasoning with large-scale and incomplete knowledge graphs. This paper advances this area of research by addressing the uncertainty inherent in knowledge. While the uncertain nature of knowledge is widely recognized in the real world, it does not align seamlessly with the first-order logic that underpins existing studies. To bridge this gap, we explore the soft queries on uncertain knowledge, inspired by the framework of soft constraint programming. We propose a neural symbolic approach that incorporates both forward inference and backward calibration to answer soft queries on large-scale, incomplete, and uncertain knowledge graphs. Theoretical discussions demonstrate that our method avoids catastrophic cascading errors in the forward inference while maintaining the same complexity as state-of-the-art symbolic methods for complex logical queries. Empirical results validate the superior performance of our backward calibration compared to extended query embedding methods and neural symbolic approaches.