Abstract
Complex Query Answering (CQA) has been extensively studied in recent years. In order to model data that is closer to real-world distribution, knowledge graphs with different modalities have been introduced. Triple KGs, as the classic KGs composed of entities and relations of arity 2, have limited representation of real-world facts. Real-world data is more sophisticated. While hyper-relational graphs have been introduced, there are limitations in representing relationships of varying arity that contain entities with equal contributions. To address this gap, we sampled new CQA datasets: JF17k-HCQA and M-FB15k-HCQA. Each dataset contains various query types that include logical operations such as projection, negation, conjunction, and disjunction. In order to answer knowledge hypergraph (KHG) existential first-order queries, we propose a two-stage transformer model, the Logical Knowledge Hypergraph Transformer (LKHGT), which consists of a Projection Encoder for atomic projection and a Logical Encoder for complex logical operations. Both encoders are equipped with Type Aware Bias (TAB) for capturing token interactions. Experimental results on CQA datasets show that LKHGT is a state-of-the-art CQA method over KHG and is able to generalize to out-of-distribution query types.
Abstract (translated)
近年来，复杂查询回答（CQA）受到了广泛的研究。为了更好地模拟接近真实世界的数据分布，引入了不同模态的知识图谱。传统的三元组知识图谱（Triple KGs），由arity为2的实体和关系组成，对现实世界事实的表现能力有限。而实际数据更加复杂多变。虽然超关系图已被提出以解决这一问题，但在表示包含同等贡献实体的不同arity的关系时仍然存在局限性。为了弥补这个空白，我们抽取了新的CQA数据集：JF17k-HCQA和M-FB15k-HCQA。这些数据集中包含了包括投影、否定、合取（与）和析取（或）等逻辑操作在内的各种查询类型。为了解答知识超图（KHG）的存在一阶查询，我们提出了一个两阶段的Transformer模型——逻辑知识超图变换器（LKHGT），该模型由用于原子投影的Projection Encoder和用于复杂逻辑运算的Logical Encoder组成。这两个编码器都配备了能够捕捉令牌交互作用的类型感知偏差（Type Aware Bias, TAB）。在CQA数据集上的实验结果表明，LKHGT是处理知识超图上查询的一种最先进的方法，并且能够在分布外的查询类型上进行泛化。
URL
https://arxiv.org/abs/2504.16537
