arXiv cs.AI· Cosimo Gregucci, Bo Xiong, Daniel Hernandez, Lorenzo Loconte, Pasquale Minervini, Steffen Staab, Antonio Vergari·· 3 天前AI 评分34
知识图谱复杂查询问答（CQA）基准真的复杂吗？ICML 2025 研究揭示现有基准缺陷并提出新基准
Is Complex Query Answering Really Complex?
AI 导读
研究发现现有知识图谱复杂查询问答（CQA）基准存在缺陷：部分查询类型中高达 98% 的查询可归约为链接预测等更简单的问题，导致对领域进展的认知被扭曲。SOTA CQA 模型在无法归约的查询上性能显著下降。作者据此提出一组更具挑战性的新基准，要求模型进行多跳推理，系统实验显示当前 CQA 方法远未达标。
正文 · 原文
Abstract: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.
| Comments: | ICML 2025 |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2410.12537 [cs.LG] |
| (or arXiv:2410.12537v4 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2410.12537 arXiv-issued DOI via DataCite |
Submission history
From: Cosimo Gregucci [view email]
[v1]
Wed, 16 Oct 2024 13:19:03 UTC (384 KB)
[v2]
Tue, 18 Feb 2025 12:40:13 UTC (483 KB)
[v3]
Thu, 3 Jul 2025 08:36:22 UTC (486 KB)
[v4]
Mon, 12 Oct 2026 16:21:44 UTC (481 KB)
来源：arXiv cs.AI · arxiv.org