$\text{EFO}_{k}$-CQA: Towards Knowledge Graph Complex Query Answering beyond Set Operation

TL;DR

This paper introduces a new dataset and framework for complex knowledge graph query answering that extends existing set operation-based methods, enabling better evaluation of reasoning over incomplete knowledge.

Contribution

It proposes a comprehensive framework for data generation, model training, and evaluation of $ ext{EFO}_{k}$ queries, and constructs a new dataset with diverse query types to improve benchmarking.

Findings

The dataset includes 741 query types for thorough evaluation.

Existing datasets are systematically biased, affecting method development.

Query hardness impacts the performance of reasoning methods.

Abstract

To answer complex queries on knowledge graphs, logical reasoning over incomplete knowledge is required due to the open-world assumption. Learning-based methods are essential because they are capable of generalizing over unobserved knowledge. Therefore, an appropriate dataset is fundamental to both obtaining and evaluating such methods under this paradigm. In this paper, we propose a comprehensive framework for data generation, model training, and method evaluation that covers the combinatorial space of Existential First-order Queries with multiple variables ($\text{EFO}_{k}$). The combinatorial query space in our framework significantly extends those defined by set operations in the existing literature. Additionally, we construct a dataset, $\text{EFO}_{k}$-CQA, with 741 types of query for empirical evaluation, and our benchmark results provide new insights into how query hardness affects the results. Furthermore, we demonstrate that the existing dataset construction process is systematically biased that hinders the appropriate development of query-answering methods, highlighting the importance of our work. Our code and data are provided in~\url{https://github.com/HKUST-KnowComp/EFOK-CQA}.