Extending Complex Logical Queries on Uncertain Knowledge Graphs
This addresses the challenge of handling uncertainty in knowledge graphs for applications like reasoning and query answering, representing an incremental improvement over prior work.
The paper tackles the problem of answering complex logical queries on uncertain knowledge graphs by proposing a neural symbolic approach with forward inference and backward calibration, achieving superior performance compared to existing methods.
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.