Is Complex Query Answering Really Complex?
This work addresses the problem of overestimating progress in complex query answering for researchers and practitioners by exposing benchmark flaws and proposing more realistic evaluations.
The paper reveals that existing benchmarks for complex query answering on knowledge graphs are not truly complex, as up to 98% of queries can be reduced to simpler link prediction tasks, and it introduces new, more challenging benchmarks that expose significant performance drops in state-of-the-art models.
Complex query answering (CQA) on knowledge graphs (KGs) is gaining momentum as a challenging reasoning task. In this paper, we show that the current benchmarks for CQA might not be as complex as we think, as the way they are built distorts our perception of progress in this field. For example, we find that in these benchmarks, most queries (up to 98% for some query types) can be reduced to simpler problems, e.g., link prediction, where only one link needs to be predicted. The performance of state-of-the-art CQA models decreases significantly when such models are evaluated on queries that cannot be reduced to easier types. Thus, we propose a set of more challenging benchmarks composed of queries that require models to reason over multiple hops and better reflect the construction of real-world KGs. In a systematic empirical investigation, the new benchmarks show that current methods leave much to be desired from current CQA methods.