$\text{EFO}_{k}$-CQA: Towards Knowledge Graph Complex Query Answering beyond Set Operation
This work addresses the need for comprehensive datasets and evaluation frameworks for knowledge graph complex query answering, which is incremental as it extends existing query spaces and highlights systematic biases.
The authors tackled the problem of answering complex queries on knowledge graphs by proposing a framework for data generation, model training, and evaluation that covers a broader combinatorial space of existential first-order queries (EFO_k), beyond set operations, and constructed a dataset with 741 query types to benchmark methods and reveal biases in existing datasets.
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}.